Upload 24 files

.gitignore

@@ -0,0 +1,427 @@
+## Ignore Visual Studio temporary files, build results, and
+## files generated by popular Visual Studio add-ons.
+##
+## Get latest from https://github.com/github/gitignore/blob/master/VisualStudio.gitignore
+
+# User-specific files
+*.rsuser
+*.suo
+*.user
+*.userosscache
+*.sln.docstates
+
+# User-specific files (MonoDevelop/Xamarin Studio)
+*.userprefs
+
+# Mono auto generated files
+mono_crash.*
+
+# Build results
+[Dd]ebug/
+[Dd]ebugPublic/
+[Rr]elease/
+[Rr]eleases/
+x64/
+x86/
+[Aa][Rr][Mm]/
+[Aa][Rr][Mm]64/
+bld/
+[Bb]in/
+[Oo]bj/
+[Ll]og/
+[Ll]ogs/
+
+# Visual Studio 2015/2017 cache/options directory
+.vs/
+# Uncomment if you have tasks that create the project's static files in wwwroot
+#wwwroot/
+
+# Visual Studio 2017 auto generated files
+Generated\ Files/
+
+# MSTest test Results
+[Tt]est[Rr]esult*/
+[Bb]uild[Ll]og.*
+
+# NUnit
+*.VisualState.xml
+TestResult.xml
+nunit-*.xml
+
+# Build Results of an ATL Project
+[Dd]ebugPS/
+[Rr]eleasePS/
+dlldata.c
+
+# Benchmark Results
+BenchmarkDotNet.Artifacts/
+
+# .NET Core
+project.lock.json
+project.fragment.lock.json
+artifacts/
+
+# StyleCop
+StyleCopReport.xml
+
+# Files built by Visual Studio
+*_i.c
+*_p.c
+*_h.h
+*.ilk
+*.meta
+*.obj
+*.iobj
+*.pch
+*.pdb
+*.ipdb
+*.pgc
+*.pgd
+*.rsp
+*.sbr
+*.tlb
+*.tli
+*.tlh
+*.tmp
+*.tmp_proj
+*_wpftmp.csproj
+*.log
+*.vspscc
+*.vssscc
+.builds
+*.pidb
+*.svclog
+*.scc
+
+# Chutzpah Test files
+_Chutzpah*
+
+# Visual C++ cache files
+ipch/
+*.aps
+*.ncb
+*.opendb
+*.opensdf
+*.sdf
+*.cachefile
+*.VC.db
+*.VC.VC.opendb
+
+# Visual Studio profiler
+*.psess
+*.vsp
+*.vspx
+*.sap
+
+# Visual Studio Trace Files
+*.e2e
+
+# TFS 2012 Local Workspace
+$tf/
+
+# Guidance Automation Toolkit
+*.gpState
+
+# ReSharper is a .NET coding add-in
+_ReSharper*/
+*.[Rr]e[Ss]harper
+*.DotSettings.user
+
+# TeamCity is a build add-in
+_TeamCity*
+
+# DotCover is a Code Coverage Tool
+*.dotCover
+
+# AxoCover is a Code Coverage Tool
+.axoCover/*
+!.axoCover/settings.json
+
+# Visual Studio code coverage results
+*.coverage
+*.coveragexml
+
+# NCrunch
+_NCrunch_*
+.*crunch*.local.xml
+nCrunchTemp_*
+
+# MightyMoose
+*.mm.*
+AutoTest.Net/
+
+# Web workbench (sass)
+.sass-cache/
+
+# Installshield output folder
+[Ee]xpress/
+
+# DocProject is a documentation generator add-in
+DocProject/buildhelp/
+DocProject/Help/*.HxT
+DocProject/Help/*.HxC
+DocProject/Help/*.hhc
+DocProject/Help/*.hhk
+DocProject/Help/*.hhp
+DocProject/Help/Html2
+DocProject/Help/html
+
+# Click-Once directory
+publish/
+
+# Publish Web Output
+*.[Pp]ublish.xml
+*.azurePubxml
+# Note: Comment the next line if you want to checkin your web deploy settings,
+# but database connection strings (with potential passwords) will be unencrypted
+*.pubxml
+*.publishproj
+
+# Microsoft Azure Web App publish settings. Comment the next line if you want to
+# checkin your Azure Web App publish settings, but sensitive information contained
+# in these scripts will be unencrypted
+PublishScripts/
+
+# NuGet Packages
+*.nupkg
+# NuGet Symbol Packages
+*.snupkg
+# The packages folder can be ignored because of Package Restore
+**/[Pp]ackages/*
+# except build/, which is used as an MSBuild target.
+!**/[Pp]ackages/build/
+# Uncomment if necessary however generally it will be regenerated when needed
+#!**/[Pp]ackages/repositories.config
+# NuGet v3's project.json files produces more ignorable files
+*.nuget.props
+*.nuget.targets
+
+# Microsoft Azure Build Output
+csx/
+*.build.csdef
+
+# Microsoft Azure Emulator
+ecf/
+rcf/
+
+# Windows Store app package directories and files
+AppPackages/
+BundleArtifacts/
+Package.StoreAssociation.xml
+_pkginfo.txt
+*.appx
+*.appxbundle
+*.appxupload
+
+# Visual Studio cache files
+# files ending in .cache can be ignored
+*.[Cc]ache
+# but keep track of directories ending in .cache
+!?*.[Cc]ache/
+
+# Others
+ClientBin/
+~$*
+*~
+*.dbmdl
+*.dbproj.schemaview
+*.jfm
+*.pfx
+*.publishsettings
+orleans.codegen.cs
+
+# Including strong name files can present a security risk
+# (https://github.com/github/gitignore/pull/2483#issue-259490424)
+#*.snk
+
+# Since there are multiple workflows, uncomment next line to ignore bower_components
+# (https://github.com/github/gitignore/pull/1529#issuecomment-104372622)
+#bower_components/
+
+# RIA/Silverlight projects
+Generated_Code/
+
+# Backup & report files from converting an old project file
+# to a newer Visual Studio version. Backup files are not needed,
+# because we have git ;-)
+_UpgradeReport_Files/
+Backup*/
+UpgradeLog*.XML
+UpgradeLog*.htm
+ServiceFabricBackup/
+*.rptproj.bak
+
+# SQL Server files
+*.mdf
+*.ldf
+*.ndf
+
+# Business Intelligence projects
+*.rdl.data
+*.bim.layout
+*.bim_*.settings
+*.rptproj.rsuser
+*- [Bb]ackup.rdl
+*- [Bb]ackup ([0-9]).rdl
+*- [Bb]ackup ([0-9][0-9]).rdl
+
+# Microsoft Fakes
+FakesAssemblies/
+
+# GhostDoc plugin setting file
+*.GhostDoc.xml
+
+# Node.js Tools for Visual Studio
+.ntvs_analysis.dat
+node_modules/
+
+# Visual Studio 6 build log
+*.plg
+
+# Visual Studio 6 workspace options file
+*.opt
+
+# Visual Studio 6 auto-generated workspace file (contains which files were open etc.)
+*.vbw
+
+# Visual Studio LightSwitch build output
+**/*.HTMLClient/GeneratedArtifacts
+**/*.DesktopClient/GeneratedArtifacts
+**/*.DesktopClient/ModelManifest.xml
+**/*.Server/GeneratedArtifacts
+**/*.Server/ModelManifest.xml
+_Pvt_Extensions
+
+# Paket dependency manager
+.paket/paket.exe
+paket-files/
+
+# FAKE - F# Make
+.fake/
+
+# CodeRush personal settings
+.cr/personal
+
+# Python Tools for Visual Studio (PTVS)
+__pycache__/
+*.pyc
+
+# Cake - Uncomment if you are using it
+# tools/**
+# !tools/packages.config
+
+# Tabs Studio
+*.tss
+
+# Telerik's JustMock configuration file
+*.jmconfig
+
+# BizTalk build output
+*.btp.cs
+*.btm.cs
+*.odx.cs
+*.xsd.cs
+
+# OpenCover UI analysis results
+OpenCover/
+
+# Azure Stream Analytics local run output
+ASALocalRun/
+
+# MSBuild Binary and Structured Log
+*.binlog
+
+# NVidia Nsight GPU debugger configuration file
+*.nvuser
+
+# MFractors (Xamarin productivity tool) working folder
+.mfractor/
+
+# Local History for Visual Studio
+.localhistory/
+
+# BeatPulse healthcheck temp database
+healthchecksdb
+
+# Backup folder for Package Reference Convert tool in Visual Studio 2017
+MigrationBackup/
+
+# Ionide (cross platform F# VS Code tools) working folder
+.ionide/
+
+vidqa_data/
+media/
+temp/
+legen_burned_*/
+legen_srt_*/
+log-vidqa.txt
+legen_errors.txt
+legen-errors.txt
+.vscode/launch.json
+
+**.srt
+**.mp4
+**.webm
+**.mkv
+**.avi
+**.mov
+**.wmv
+**.flv
+**.vob
+**.mts
+**.m2ts
+**.ts
+**.yuv
+**.mpg
+**.mpga
+**.mp2
+**.mpeg
+**.mpe
+**.mpv
+**.m2v
+**.m4v
+**.3gp
+**.3g2
+**.nsv
+**.aa
+**.aac
+**.aax
+**.act
+**.aiff
+**.alac
+**.amr
+**.ape
+**.au
+**.awb
+**.dss
+**.dvf
+**.flac
+**.gsm
+**.iklax
+**.ivs
+**.m4a
+**.m4b
+**.m4p
+**.mmf
+**.mp3
+**.mpc
+**.msv
+**.nmf
+**.ogg
+**.oga
+**.mogg
+**.opus
+**.ra
+**.rm
+**.raw
+**.rf64
+**.sln
+**.tta
+**.voc
+**.vox
+**.wav
+**.wma
+**.wv
+**.webm
+**.8svx
+**.mts

LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

README.md

@@ -1,13 +1,152 @@
----
-title: Lege
-emoji: 🌍
-colorFrom: pink
-colorTo: purple
-sdk: gradio
-sdk_version: 5.0.1
-app_file: app.py
-pinned: false
-license: gpl-3.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# LeGen
+
+![legen-wide](https://github.com/matheusbach/legen/assets/35426162/05a7acd2-52d5-43e0-8f31-7da7d6aa7c3c)
+
+
+LeGen is a Python script that uses Whisper/WhisperX AI to locally transcribes speech from media files, generating subtitle files, can translates the generated subtitles, inserts them into the mp4 container, and burns them directly into video
+
+This is very useful for making it available in another language, or even just subtitling any video that belongs to you or that you have the proper authorization to do so, be it a film, lecture, course, presentation, interview, etc.
+
+## Run on Colab
+
+LeGen works on Google Colab, using their computing power to do the work. Aceess the link to [run on Google Colab](https://colab.research.google.com/github/matheusbach/legen/blob/main/legen.ipynb)
+
+ <a href='https://colab.research.google.com/github/matheusbach/legen/blob/main/legen.ipynb' style='padding-left: 0.5rem;'><img src='https://colab.research.google.com/assets/colab-badge.svg' alt='Google Colab'></a>
+
+## Install locally:
+
+Install FFMpeg from [FFMPeg Oficial Site](https://ffmpeg.org/download.html) or from your linux package manager. _If using windows, prefer gyan_dev release full `choco install ffmpeg-full`_
+
+Install [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git)
+
+Install [Python](https://www.python.org/downloads/) 3.8 or up. _If using windows, select "Add to PATH" option when installing_
+
+Clone LeGen using git
+```sh
+git clone https://github.com/matheusbach/legen.git
+cd legen
+```
+
+Install requirements using pip. Is recommended to create a virtual environment (venv) as a good practice
+```sh
+pip3 install -r requirements.txt --upgrade
+```
+
+### GPU compatibility
+
+If having troubles with GPU compatibility, get [PyTorch](https://pytorch.org/get-started/locally/) for your GPU.
+
+_And done. Now you can use LeGen_
+
+### Update
+
+For dry-run update, use in legen folder:
+```sh
+git fetch && git reset --hard origin/main && git pull
+pip3 install -r requirements.txt --upgrade --force-reinstall
+```
+
+## Run locally:
+
+To use LeGen, run the following command:
+
+The minimum comand line is:
+
+```sh
+python3 legen.py -i [input_path]
+```
+
+Users could for example also translate generated subtitles for other language like portuguese (pt) adding `--translate pt` to the command line
+
+
+Full options list are described bellow:
+
+- `-i`, `--input_path`: Specifies the path to the media files. This can be a folder containing files or an individual file. Example: `LeGen -i /path/to/media/files`.
+
+- `--norm`: Normalizes folder times and runs vidqa on the input path before starting to process files. Useful for synchronizing timestamps across multiple media files.
+
+- `-ts:e`, `--transcription_engine`: Specifies the transcription engine to use. Possible values are "whisperx" and "whisper". Default is "whisperx".
+
+- `-ts:m`, `--transcription_model`: Specifies the path or name of the Whisper transcription model. A larger model will consume more resources and be slower, but with better transcription quality. Possible values: tiny, base, small, medium (default), large, ...
+
+- `-ts:d`, `--transcription_device`: Specifies the device to run the transcription through Whisper. Possible values: auto (default), cpu, cuda.
+
+- `-ts:c`, `--transcription_compute_type`: Specifies the quantization for the neural network. Possible values: auto (default), int8, int8_float32, int8_float16, int8_bfloat16, int16, float16, bfloat16, float32.
+
+- `-ts:b`, `--transcription_batch`: Specifies the number of simultaneous segments being transcribed. Higher values will speed up processing. If you have low RAM/VRAM, long duration media files or have buggy subtitles, reduce this value to avoid issues. Only works using transcription_engine whisperx. Default is 4.
+
+- `--translate`: Translates subtitles to a language code if they are not the same as the original. The language code should be specified after the equals sign. For example, `LeGen --translate=fr` would translate the subtitles to French.
+
+- `--input_lang`: Indicates (forces) the language of the voice in the input media. Default is "auto".
+
+- `-c:v`, `--codec_video`: Specifies the target video codec. Can be used to set acceleration via GPU or another video API [codec_api], if supported (ffmpeg -encoders). Examples include h264, libx264, h264_vaapi, h264_nvenc, hevc, libx265 hevc_vaapi, hevc_nvenc, hevc_cuvid, hevc_qsv, hevc_amf. Default is h264.
+
+- `-c:a`, `--codec_audio`: Specifies the target audio codec. Default is aac. Examples include aac, libopus, mp3, vorbis.
+
+- `-o:s`, `--output_softsubs`: Specifies the path to the folder or output file for the video files with embedded softsub (embedded in the mp4 container and .srt files). Default is "softsubs_" followed by the input path.
+
+- `-o:h`, `--output_hardsubs`: Specifies the output folder path for video files with burned-in captions and embedded in the mp4 container. Default is "hardsubs_" followed by the input path.
+
+- `--overwrite`: Overwrites existing files in output directories. By default, this option is false.
+
+- `--disable_srt`: Disables .srt file generation and doesn't insert subtitles in the mp4 container of output_softsubs. By default, this option is false.
+
+- `--disable_softsubs`: Doesn't insert subtitles in the mp4 container of output_softsubs. This option continues generating .srt files. By default, this option is false.
+
+- `--disable_hardsubs`: Disables subtitle burn in output_hardsubs. By default, this option is false.
+
+- `--copy_files`: Copies other (non-video) files present in the input directory to output directories. Only generates the subtitles and videos. By default, this option is false.
+
+Each of these options provides control over various aspects of the video processing workflow. Make sure to refer to the documentation or help message (`LeGen --help`) for more details on each option[Source 0](https://docs.python.org/3/library/argparse.html)[Source 2](https://realpython.com/command-line-interfaces-python-argparse/).
+
+## Dependencies
+
+LeGen requires the following **pip** dependencies to be installed:
+- deep_translator
+- ffmpeg_progress_yield
+- openai_whisper
+- pysrt
+- torch
+- tqdm
+- whisper
+- vidqa
+- matheusbach/whisperx (fork from m-bain/whisperx)
+
+This dependencies can be installed and updated with ```pip install -r requirements.txt --upgrade```
+
+You also need to [install FFmpeg](https://ffmpeg.org/download.html)
+
+## Contributing
+
+Contributions are welcome. Submit your pull request ❤️
+
+## Issues, Doubts
+
+Not being able to use the software, or encountering an error? open an [issue](https://github.com/matheusbach/legen/issues/new)
+
+## Telegram Group
+
+Welcome and don't be a sick. We are brazilian, but you can write in other language if you want. https://t.me/+c0VRonlcd9Q2YTAx
+
+## Video Tutorials
+
+[PT-BR] [SEMI-OUTDATED] [**Tutorial - LeGen no Google Colab**](https://odysee.com/@legen_software:d/legen_no_colab:0)
+
+## Donations
+
+You can donate to project using:
+Monero (XMR): ```86HjTCsiaELEoNhH96rTf3ezGMXgKmHjqFrNmca2tesCESdCTZvRvQ9QWQXPGDtmaZhKz4ryHCdZXFzdbmtGahVa5VMLJnx```
+LivePix: https://livepix.gg/legendonate
+
+### Donators
+- Picasso Neves
+- Erasmo de Souza Mora
+- viniciuspro
+- Igor
+- NiNi
+- PopularC
+
+
+## License
+
+This project is licensed under the terms of the [GNU GPLv3](https://choosealicense.com/licenses/gpl-3.0/).

app.py

@@ -1 +1,315 @@
-print('test')
+import gradio as gr
+import os
+from pathlib import Path
+import subprocess
+import asyncio
+import threading
+import signal
+import sys
+import re
+from typing import Optional, List
+from i18n.i18n import I18nAuto
+from header import badges, description
+i18n = I18nAuto()
+
+# Variável global para armazenar o processo atual
+current_process: Optional[subprocess.Popen] = None
+
+# Força o uso de UTF-8 para o Python
+os.environ["PYTHONIOENCODING"] = "utf-8"
+
+# Para garantir que a codificação esteja correta no terminal
+if sys.platform == "win32":
+    os.system('chcp 65001')
+
+# Redefine a configuração de codificação da saída padrão
+sys.stdout.reconfigure(encoding='utf-8')
+sys.stderr.reconfigure(encoding='utf-8')
+
+def clean_ansi(text: str) -> str:
+    """Remove códigos ANSI e limpa o texto para exibição"""
+    ansi_escape = re.compile(r'\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])')
+    return ansi_escape.sub('', text)
+
+def process_output(line: str, progress: gr.Progress) -> str:
+    """Processa uma linha de saída e atualiza o progresso"""
+    clean_line = clean_ansi(line.strip())
+    
+    # Procura por padrões de progresso
+    if "%" in clean_line:
+        try:
+            # Extrai o número do progresso
+            progress_match = re.search(r'(\d+\.?\d*)%', clean_line)
+            if progress_match:
+                progress_value = float(progress_match.group(1)) / 100
+                progress(progress_value, desc=clean_line)
+        except ValueError:
+            pass
+    
+    return clean_line
+
+def stop_process():
+    global current_process
+    if current_process:
+        try:
+            if os.name == 'nt':
+                current_process.terminate()
+            else:
+                os.killpg(os.getpgid(current_process.pid), signal.SIGTERM)
+            current_process.wait(timeout=5)  # Espera até 5 segundos pelo término
+        except subprocess.TimeoutExpired:
+            if os.name == 'nt':
+                current_process.kill()
+            else:
+                os.killpg(os.getpgid(current_process.pid), signal.SIGKILL)
+        current_process = None
+        return "Process stopped by user"
+    return "No process running"
+
+def run_legen(
+    input_path,
+    transcription_engine,
+    transcription_model,
+    compute_type,
+    device,
+    batch_size,
+    input_lang,
+    translate_lang,
+    video_codec,
+    audio_codec,
+    output_softsubs_path,
+    output_hardsubs_path,
+    normalize,
+    overwrite,
+    copy_files,
+    disable_srt,
+    disable_softsubs,
+    disable_hardsubs,
+    progress=gr.Progress()
+):
+    global current_process
+    
+    if not input_path:
+        return "Please provide an input path"
+    
+    if not os.path.exists(input_path):
+        return "Input path does not exist"
+        
+    if not os.path.exists("legen.py"):
+        return "legen.py not found in current directory"
+
+    cmd = ["python", "legen.py", "-i", input_path]
+
+    # Adiciona as flags baseadas nos checkboxes
+    if normalize: cmd.append("--norm")
+    if overwrite: cmd.append("--overwrite")
+    if copy_files: cmd.append("--copy_files")
+    if disable_srt: cmd.append("--disable_srt")
+    if disable_softsubs: cmd.append("--disable_softsubs")
+    if disable_hardsubs: cmd.append("--disable_hardsubs")
+
+    # Adiciona configurações de transcrição
+    cmd.extend(["-ts:e", transcription_engine])
+    cmd.extend(["-ts:m", transcription_model])
+    cmd.extend(["-ts:d", device])
+    cmd.extend(["-ts:c", compute_type])
+    cmd.extend(["-ts:b", str(batch_size)])
+
+    if translate_lang != "none":
+        cmd.extend(["--translate", translate_lang])
+    if input_lang != "auto":
+        cmd.extend(["--input_lang", input_lang])
+
+    # Adiciona configurações de codec
+    cmd.extend(["-c:v", video_codec])
+    cmd.extend(["-c:a", audio_codec])
+
+    # Adiciona caminhos de saída
+    if output_softsubs_path:
+        cmd.extend(["-o:s", output_softsubs_path])
+    if output_hardsubs_path:
+        cmd.extend(["-o:h", output_hardsubs_path])
+
+    try:
+        startupinfo = None
+        if os.name == 'nt':
+            startupinfo = subprocess.STARTUPINFO()
+            startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
+
+        current_process = subprocess.Popen(
+            cmd,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.STDOUT,  # Combina stderr com stdout
+            text=True,
+            bufsize=1,
+            universal_newlines=True,
+            startupinfo=startupinfo,
+            encoding='utf-8',
+            errors='replace',
+            preexec_fn=None if os.name == 'nt' else os.setsid
+        )
+
+        output_lines: List[str] = []
+        last_progress_update = 0
+
+        while True:
+            line = current_process.stdout.readline()
+            
+            if not line and current_process.poll() is not None:
+                break
+                
+            if line:
+                try:
+                    clean_line = process_output(line, progress)
+                    output_lines.append(clean_line)
+                    
+                    # Atualiza a saída periodicamente
+                    if len(output_lines) - last_progress_update >= 5:
+                        yield "\n".join(output_lines)
+                        last_progress_update = len(output_lines)
+                        
+                except Exception as e:
+                    output_lines.append(f"Error processing output: {str(e)}")
+
+        if current_process.poll() == 0:
+            final_output = "Processing completed successfully!\n\n" + "\n".join(output_lines)
+        else:
+            final_output = f"Process ended with error code {current_process.poll()}\n\n" + "\n".join(output_lines)
+        
+        current_process = None
+        return final_output
+
+    except Exception as e:
+        current_process = None
+        return f"Error: {str(e)}"
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown(badges)
+    gr.Markdown(description)
+    title="LeGen"
+    
+    with gr.Row():
+        with gr.Column():
+            # Input Section
+            with gr.Group():
+                input_path = gr.Textbox(label=i18n("Input Path"), placeholder=i18n("Enter path to file or folder"))
+
+            # Transcription Settings
+            with gr.Group():
+                transcription_engine = gr.Dropdown(
+                    choices=["whisperx", "whisper"],
+                    value="whisperx",
+                    label=i18n("Transcription Engine")
+                )
+                with gr.Row():
+                    transcription_model = gr.Dropdown(
+                        choices=["tiny", "base", "small", "medium", "large", "large-v1", "large-v2", "large-v3", "large-v3-turbo",],
+                        value="large-v3",
+                        label=i18n("Model")
+                    )
+                    compute_type = gr.Dropdown(
+                        choices=["auto", "int8", "float16", "float32"],
+                        value="auto",
+                        label=i18n("Compute Type")
+                    )
+                with gr.Row():
+                    device = gr.Dropdown(
+                        choices=["auto", "cpu", "cuda"],
+                        value="auto",
+                        label=i18n("Device")
+                    )
+                    batch_size = gr.Number(
+                        value=4,
+                        label=i18n("Batch Size"),
+                        precision=0
+                    )
+                with gr.Row():
+                    input_lang = gr.Dropdown(
+                        choices=["auto", "en", "es", "pt", "fr", "de", "it", "ja", "ko", "zh"],
+                        value="auto",
+                        label=i18n("Input Language")
+                    )
+                    translate_lang = gr.Dropdown(
+                        choices=["none", "en", "es", "pt", "fr", "de", "it", "ja", "ko", "zh"],
+                        value="none",
+                        label=i18n("Translate to")
+                    )
+
+        with gr.Column():
+            # Output Settings
+            with gr.Group():
+                with gr.Row():
+                    video_codec = gr.Dropdown(
+                        choices=["h264", "libx264", "h264_vaapi", "h264_nvenc", "hevc", "libx265", "hevc_vaapi"],
+                        value="h264",
+                        label=i18n("Video Codec")
+                    )
+                    audio_codec = gr.Dropdown(
+                        choices=["aac", "libopus", "mp3", "vorbis"],
+                        value="aac",
+                        label=i18n("Audio Codec")
+                    )
+                output_softsubs_path = gr.Textbox(
+                    value="softsubs_output",
+                    label=i18n("Softsubs Output Path")
+                )
+                output_hardsubs_path = gr.Textbox(
+                    value="hardsubs_output",
+                    label=i18n("Hardsubs Output Path")
+                )
+
+            # Options
+            with gr.Group():
+                with gr.Row():
+                    normalize = gr.Checkbox(label=i18n("Normalize folder times"), value=False)
+                    overwrite = gr.Checkbox(label=i18n("Overwrite existing files"), value=False)
+                    copy_files = gr.Checkbox(label=i18n("Copy non-video files"), value=False)
+                with gr.Row():
+                    disable_srt = gr.Checkbox(label=i18n("Disable SRT generation"), value=False)
+                    disable_softsubs = gr.Checkbox(label=i18n("Disable softsubs"), value=False)
+                    disable_hardsubs = gr.Checkbox(label=i18n("Disable hardsubs"), value=False)
+
+    # Run Button, Stop Button and Output
+    with gr.Row():
+        with gr.Column():
+            run_btn = gr.Button(i18n("Run LeGen"), variant="primary")
+            stop_btn = gr.Button(i18n("Stop"), variant="stop")
+        output = gr.Textbox(label=i18n("Output"), lines=5)
+
+    # Connect the run button to the processing function
+    run_btn.click(
+        fn=run_legen,
+        inputs=[
+            input_path,
+            transcription_engine,
+            transcription_model,
+            compute_type,
+            device,
+            batch_size,
+            input_lang,
+            translate_lang,
+            video_codec,
+            audio_codec,
+            output_softsubs_path,
+            output_hardsubs_path,
+            normalize,
+            overwrite,
+            copy_files,
+            disable_srt,
+            disable_softsubs,
+            disable_hardsubs
+        ],
+        outputs=output
+    )
+
+    stop_btn.click(
+        fn=stop_process,
+        inputs=[],
+        outputs=output
+    )
+    gr.Markdown("""
+                <center>WebUI Desenvolvida por Rafa.Godoy</center>
+                <center>Agradecimentos ao MatheusBach por desenvolver o LeGen</center>
+                """)
+if __name__ == "__main__":
+    demo.launch()

app_hf.py

@@ -0,0 +1,357 @@
+import gradio as gr
+import os
+from pathlib import Path
+import subprocess
+import asyncio
+import threading
+import signal
+import sys
+import re
+import shutil
+from typing import Optional, List, Tuple
+from i18n.i18n import I18nAuto
+from header import badges, description
+i18n = I18nAuto()
+
+# Variável global para armazenar o processo atual
+current_process: Optional[subprocess.Popen] = None
+
+# Força o uso de UTF-8 para o Python
+os.environ["PYTHONIOENCODING"] = "utf-8"
+
+# Para garantir que a codificação esteja correta no terminal
+if sys.platform == "win32":
+    os.system('chcp 65001')
+
+# Redefine a configuração de codificação da saída padrão
+sys.stdout.reconfigure(encoding='utf-8')
+sys.stderr.reconfigure(encoding='utf-8')
+
+# Criar diretórios necessários se não existirem
+def ensure_directories():
+    directories = ['uploaded_videos', 'softsubs_output', 'hardsubs_output']
+    for directory in directories:
+        os.makedirs(os.path.join(os.getcwd(), directory), exist_ok=True)
+    return os.path.join(os.getcwd(), 'uploaded_videos')
+
+def save_uploaded_files(files):
+    """Salva os arquivos enviados na pasta uploaded_videos"""
+    if not files:
+        return "No files uploaded"
+    
+    upload_dir = ensure_directories()
+    saved_files = []
+    
+    for file in files:
+        filename = os.path.basename(file.name)
+        destination = os.path.join(upload_dir, filename)
+        shutil.copy2(file.name, destination)
+        saved_files.append(filename)
+    
+    return f"Uploaded files: {', '.join(saved_files)}"
+
+def get_output_files() -> Tuple[List[str], List[str]]:
+    """Retorna listas de arquivos nas pastas de saída"""
+    softsubs_dir = os.path.join(os.getcwd(), 'softsubs_output')
+    hardsubs_dir = os.path.join(os.getcwd(), 'hardsubs_output')
+    
+    softsubs_files = [os.path.join(softsubs_dir, f) for f in os.listdir(softsubs_dir) if os.path.isfile(os.path.join(softsubs_dir, f))]
+    hardsubs_files = [os.path.join(hardsubs_dir, f) for f in os.listdir(hardsubs_dir) if os.path.isfile(os.path.join(hardsubs_dir, f))]
+    
+    return softsubs_files, hardsubs_files
+
+def clean_ansi(text: str) -> str:
+    """Remove códigos ANSI e limpa o texto para exibição"""
+    ansi_escape = re.compile(r'\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])')
+    return ansi_escape.sub('', text)
+
+def process_output(line: str, progress: gr.Progress) -> str:
+    """Processa uma linha de saída e atualiza o progresso"""
+    clean_line = clean_ansi(line.strip())
+    
+    if "%" in clean_line:
+        try:
+            progress_match = re.search(r'(\d+\.?\d*)%', clean_line)
+            if progress_match:
+                progress_value = float(progress_match.group(1)) / 100
+                progress(progress_value, desc=clean_line)
+        except ValueError:
+            pass
+    
+    return clean_line
+
+def stop_process():
+    global current_process
+    if current_process:
+        try:
+            if os.name == 'nt':
+                current_process.terminate()
+            else:
+                os.killpg(os.getpgid(current_process.pid), signal.SIGTERM)
+            current_process.wait(timeout=5)
+        except subprocess.TimeoutExpired:
+            if os.name == 'nt':
+                current_process.kill()
+            else:
+                os.killpg(os.getpgid(current_process.pid), signal.SIGKILL)
+        current_process = None
+        return "Process stopped by user"
+    return "No process running"
+
+def run_legen(
+    transcription_engine,
+    transcription_model,
+    compute_type,
+    device,
+    batch_size,
+    input_lang,
+    translate_lang,
+    video_codec,
+    audio_codec,
+    normalize,
+    overwrite,
+    copy_files,
+    disable_srt,
+    disable_softsubs,
+    disable_hardsubs,
+    progress=gr.Progress()
+):
+    global current_process
+    
+    input_dir = ensure_directories()
+    if not os.path.exists(input_dir) or not os.listdir(input_dir):
+        return "No files found in uploaded_videos directory"
+        
+    if not os.path.exists("legen.py"):
+        return "legen.py not found in current directory"
+
+    cmd = ["python", "legen.py", "-i", input_dir]
+
+    # Adiciona as flags baseadas nos checkboxes
+    if normalize: cmd.append("--norm")
+    if overwrite: cmd.append("--overwrite")
+    if copy_files: cmd.append("--copy_files")
+    if disable_srt: cmd.append("--disable_srt")
+    if disable_softsubs: cmd.append("--disable_softsubs")
+    if disable_hardsubs: cmd.append("--disable_hardsubs")
+
+    # Adiciona configurações de transcrição
+    cmd.extend(["-ts:e", transcription_engine])
+    cmd.extend(["-ts:m", transcription_model])
+    cmd.extend(["-ts:d", device])
+    cmd.extend(["-ts:c", compute_type])
+    cmd.extend(["-ts:b", str(batch_size)])
+
+    if translate_lang != "none":
+        cmd.extend(["--translate", translate_lang])
+    if input_lang != "auto":
+        cmd.extend(["--input_lang", input_lang])
+
+    # Adiciona configurações de codec
+    cmd.extend(["-c:v", video_codec])
+    cmd.extend(["-c:a", audio_codec])
+
+    # Adiciona caminhos de saída fixos
+    cmd.extend(["-o:s", os.path.join(os.getcwd(), "softsubs_output")])
+    cmd.extend(["-o:h", os.path.join(os.getcwd(), "hardsubs_output")])
+
+    try:
+        startupinfo = None
+        if os.name == 'nt':
+            startupinfo = subprocess.STARTUPINFO()
+            startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
+
+        current_process = subprocess.Popen(
+            cmd,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.STDOUT,
+            text=True,
+            bufsize=1,
+            universal_newlines=True,
+            startupinfo=startupinfo,
+            encoding='utf-8',
+            errors='replace',
+            preexec_fn=None if os.name == 'nt' else os.setsid
+        )
+
+        output_lines: List[str] = []
+        last_progress_update = 0
+
+        while True:
+            line = current_process.stdout.readline()
+            
+            if not line and current_process.poll() is not None:
+                break
+                
+            if line:
+                try:
+                    clean_line = process_output(line, progress)
+                    output_lines.append(clean_line)
+                    
+                    if len(output_lines) - last_progress_update >= 5:
+                        yield "\n".join(output_lines)
+                        last_progress_update = len(output_lines)
+                        
+                except Exception as e:
+                    output_lines.append(f"Error processing output: {str(e)}")
+
+        if current_process.poll() == 0:
+            final_output = "Processing completed successfully!\n\n" + "\n".join(output_lines)
+        else:
+            final_output = f"Process ended with error code {current_process.poll()}\n\n" + "\n".join(output_lines)
+        
+        current_process = None
+        return final_output
+
+    except Exception as e:
+        current_process = None
+        return f"Error: {str(e)}"
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown(badges)
+    gr.Markdown(description)
+    title = "LeGen"
+    
+    ensure_directories()  # Garante que os diretórios existam ao iniciar
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            # Upload Section
+            with gr.Group():
+                upload_files = gr.Files(
+                    label=i18n("Upload Videos"),
+                    file_types=["video"],
+                    file_count="multiple"
+                )
+                upload_button = gr.Button(i18n("Upload to processing directory"))
+
+            # Transcription Settings
+            with gr.Group():
+                transcription_engine = gr.Dropdown(
+                    choices=["whisperx", "whisper"],
+                    value="whisperx",
+                    label=i18n("Transcription Engine")
+                )
+                with gr.Row():
+                    transcription_model = gr.Dropdown(
+                        choices=["tiny", "base", "small", "medium", "large", "large-v1", "large-v2", "large-v3", "large-v3-turbo"],
+                        value="large-v3",
+                        label=i18n("Model")
+                    )
+                    compute_type = gr.Dropdown(
+                        choices=["auto", "int8", "float16", "float32"],
+                        value="auto",
+                        label=i18n("Compute Type")
+                    )
+                with gr.Row():
+                    device = gr.Dropdown(
+                        choices=["auto", "cpu", "cuda"],
+                        value="auto",
+                        label=i18n("Device")
+                    )
+                    batch_size = gr.Number(
+                        value=4,
+                        label=i18n("Batch Size"),
+                        precision=0
+                    )
+                with gr.Row():
+                    input_lang = gr.Dropdown(
+                        choices=["auto", "en", "es", "pt", "fr", "de", "it", "ja", "ko", "zh"],
+                        value="auto",
+                        label=i18n("Input Language")
+                    )
+                    translate_lang = gr.Dropdown(
+                        choices=["none", "en", "es", "pt", "fr", "de", "it", "ja", "ko", "zh"],
+                        value="none",
+                        label=i18n("Translate to")
+                    )
+
+        with gr.Column(scale=1):
+            # Output Settings
+            with gr.Group():
+                with gr.Row():
+                    video_codec = gr.Dropdown(
+                        choices=["h264", "libx264", "h264_vaapi", "h264_nvenc", "hevc", "libx265", "hevc_vaapi"],
+                        value="h264",
+                        label=i18n("Video Codec")
+                    )
+                    audio_codec = gr.Dropdown(
+                        choices=["aac", "libopus", "mp3", "vorbis"],
+                        value="aac",
+                        label=i18n("Audio Codec")
+                    )
+
+            # Options
+            with gr.Group():
+                with gr.Row():
+                    normalize = gr.Checkbox(label=i18n("Normalize folder times"), value=False)
+                    overwrite = gr.Checkbox(label=i18n("Overwrite existing files"), value=False)
+                    copy_files = gr.Checkbox(label=i18n("Copy non-video files"), value=False)
+                with gr.Row():
+                    disable_srt = gr.Checkbox(label=i18n("Disable SRT generation"), value=False)
+                    disable_softsubs = gr.Checkbox(label=i18n("Disable softsubs"), value=False)
+                    disable_hardsubs = gr.Checkbox(label=i18n("Disable hardsubs"), value=False)
+
+            # Output Files Display
+            with gr.Group():
+                softsubs_files = gr.Files(label="Softsubs Output Files", file_count="multiple", interactive=False)
+                hardsubs_files = gr.Files(label="Hardsubs Output Files", file_count="multiple", interactive=False)
+
+    # Run Button, Stop Button and Output
+    with gr.Row():
+        with gr.Column(scale=1):
+            run_btn = gr.Button(i18n("Run LeGen"), variant="primary")
+            stop_btn = gr.Button(i18n("Stop"), variant="stop")
+        output = gr.Textbox(label=i18n("Output"), lines=2, interactive=False, elem_id="output")
+
+    # Event handlers
+    upload_button.click(
+        fn=save_uploaded_files,
+        inputs=[upload_files],
+        outputs=[output]
+    )
+
+    def update_output_files():
+        softsubs_files, hardsubs_files = get_output_files()
+        return softsubs_files, hardsubs_files
+
+    # Connect the run button to the processing function
+    run_btn.click(
+        fn=run_legen,
+        inputs=[
+            transcription_engine,
+            transcription_model,
+            compute_type,
+            device,
+            batch_size,
+            input_lang,
+            translate_lang,
+            video_codec,
+            audio_codec,
+            normalize,
+            overwrite,
+            copy_files,
+            disable_srt,
+            disable_softsubs,
+            disable_hardsubs
+        ],
+        outputs=output
+    ).then(
+        fn=update_output_files,
+        inputs=[],
+        outputs=[softsubs_files, hardsubs_files]
+    )
+
+    stop_btn.click(
+        fn=stop_process,
+        inputs=[],
+        outputs=output
+    )
+
+    gr.Markdown("""
+                <center>WebUI Desenvolvida por Rafa.Godoy</center>
+                <center>Agradecimentos ao MatheusBach por desenvolver o LeGen</center>
+                """)
+
+if __name__ == "__main__":
+    demo.launch()

ffmpeg_utils.py

@@ -0,0 +1,165 @@
+import base64
+import os
+import re
+import subprocess
+from pathlib import Path
+import sys
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+from ffmpeg_progress_yield import FfmpegProgress
+from tqdm import tqdm
+
+import file_utils
+
+
+def insert_subtitle(input_media_path: Path, subtitles_path: [Path], burn_subtitles: bool, output_video_path: Path, codec_video: str = "h264", codec_audio: str = "aac"):
+    # use only valid srt files
+    subtitles_path: [Path] = file_utils.validate_files(subtitles_path)
+
+    # insert in comand the basics of ffmpeg
+    cmd_ffmpeg = ["ffmpeg", "-y"]
+    cmd_ffmpeg_input_map = []
+
+    # add ffmpeg input main media
+    cmd_ffmpeg.extend(["-i", "file:" + input_media_path.as_posix()])
+    # map video stream, audio, subtitle, data and metadata
+    map_index = cmd_ffmpeg.count("-i") - 1
+    cmd_ffmpeg_input_map.extend(["-map", f"{map_index}:V?", "-map", f"{map_index}:a",
+                                 "-ignore_unknown"])
+
+    # detect if input has video channels
+    result: str = subprocess.run(["ffprobe", "-i", "file:" + input_media_path.as_posix(), "-show_streams",
+                                 "-select_streams", "V", "-loglevel", "error"], capture_output=True, text=True).stdout
+    no_video = True if result is None or "DISPOSITION:attached_pic=0" not in result else False
+
+    # if input has no video channels, map a 1280x720 black screen
+    if no_video:
+        # create a background image if media is only audio
+        background_tempfile: file_utils.TempFile = file_utils.TempFile(
+            "", ".jpeg")
+
+        # create a 1280x720 jpeg image
+        with open(file=background_tempfile.getpath(), mode="wb") as file:
+            file.write(base64.b64decode("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"))
+
+        # get input media duration
+        duration_sec = subprocess.run(["ffprobe", "-i", "file:" + input_media_path.as_posix(), "-show_entries", "format=duration", "-v", "quiet", "-of", "csv=p=0"],
+                                      capture_output=True, text=True).stdout.split("\n")[0].split('.')[0]
+
+        cmd_ffmpeg.extend(["-t", f"{duration_sec}", "-loop", "1",
+                          "-framerate", "10", "-i", background_tempfile.getpath().as_posix()])
+        map_index = cmd_ffmpeg.count("-i") - 1
+        # unmap #0, remap #0 with no video, map #1 (generated video from image)
+        cmd_ffmpeg_input_map.extend(
+            ["-map", "-0", "-map", f"0:a", "-map", f"0:d?", "-map", f"0:t?", "-map", f"{map_index}:V", "-ignore_unknown"])
+
+    # map each subtitle
+    for i, subtitle in enumerate(subtitles_path):
+        cmd_ffmpeg.extend(["-i", "file:" + subtitle.as_posix()])
+        map_index = cmd_ffmpeg.count("-i") - 1
+        cmd_ffmpeg_input_map.extend(["-map", f"{map_index}:s"])
+
+    # add comand to burn subtitles if its demanded and has at least one valid subtitle in the array. Burn the first one. Also ensure hwupload if necessary
+    vf_hwupload = True if codec_video.endswith(
+        ("_nvenc", "_amf", "_v4l2m2m", "_qsv", "_vaapi", "_videotoolbox", "_cuvid")) else False
+    hw_device = codec_video.split("_")[-1] if vf_hwupload else None
+    # set hw_device as cuda if api is nvenc or cuvid
+    if hw_device == "nvenc" or hw_device == "cuvid":
+        hw_device = "cuda"
+        vf_hwupload = False
+
+    # set hw_device as vaapi if api is v4l2m2m or amf
+    if hw_device == "v4l2m2m" or hw_device == "amf":
+        hw_device = "vaapi"
+
+    if burn_subtitles and len(subtitles_path) > 0:
+        # create temp file for .srt
+        srt_temp = file_utils.TempFile(
+            "", file_ext=".srt")
+
+        file_utils.copy_file_if_different(
+            subtitles_path[0], srt_temp.getpath(), True)
+
+        # align subtitles to botton center if hass video and to center center if only audio with black screen
+        sub_align = 10 if no_video else 2
+
+        # insert scale, subtitles filter and hwupload if required
+        # scale at minimul height of 480p. it also will make the dimensions divisible by 2
+        cmd_ffmpeg.extend(
+            ["-vf", f"format=nv12, scale='ceil((max(480,ih)*iw/ih)/2)*2:ceil(max(480,ih)/2)*2', subtitles=\'{add_ffmpeg_escape_chars(srt_temp.temp_file.name)}\':force_style='Alignment={sub_align},Fontname=Jost,PrimaryColour=&H03fcff,Fontsize=18,BackColour=&H80000000,Bold=1,Spacing=0.09,Outline=1,Shadow=0,MarginL=10,MarginR=10'" + (', hwupload' if vf_hwupload else '')])
+    else:
+        if vf_hwupload:
+            cmd_ffmpeg.extend(["-vf", f"format=nv12, hwupload"])
+        burn_subtitles = False
+
+    cmd_ffmpeg.extend(cmd_ffmpeg_input_map)
+
+    # init a hw_device if hwupload is set on video filters
+    if hw_device is not None:
+        cmd_ffmpeg.extend(["-init_hw_device", hw_device])
+
+    # add the remaining parameters and output path
+    cmd_ffmpeg.extend(["-c:V", codec_video, "-c:a", codec_audio, "-c:s", "mov_text",
+                        "-pix_fmt", "yuv420p", "-movflags", "+faststart",
+                       "-sws_flags", "bicubic+accurate_rnd+full_chroma_int+full_chroma_inp",
+                       "file:" + output_video_path.as_posix()])
+
+    # run FFmpeg command with a fancy progress bar
+    ff = FfmpegProgress(cmd_ffmpeg)
+    with tqdm(total=100, position=0, ascii="░▒█", desc="Inserting subtitles" if not burn_subtitles else "Burning subtitles", unit="%", unit_scale=True, leave=True, bar_format="{desc} [{bar}] {percentage:3.0f}% | {rate_fmt}{postfix} | ETA: {remaining} | ⏱: {elapsed}") as pbar:
+        for progress in ff.run_command_with_progress():
+            pbar.update(progress - pbar.n)
+
+    # destroy unecessary file
+    if 'srt_temp' in locals():
+        srt_temp.destroy()
+
+
+def extract_audio_wav(input_media_path: Path, output_path: Path):
+    # set the FFMpeg command
+    cmd_ffmpeg = ["ffmpeg", "-y", "-i", "file:" + input_media_path.as_posix(),
+                  "-vn", "-c:a", "pcm_s16le", "-ac", "1", "-ar", "16000", "file:" + output_path.as_posix()]
+
+    # run FFmpeg command with a fancy progress bar
+    ff = FfmpegProgress(cmd_ffmpeg)
+    with tqdm(total=100, position=0, ascii="░▒█", desc="Extracting audio", unit="%", unit_scale=True, leave=True, bar_format="{desc} {percentage:3.0f}% | ETA: {remaining} | ⏱: {elapsed}") as pbar:
+        for progress in ff.run_command_with_progress():
+            pbar.update(progress - pbar.n)
+
+
+def extract_short_wav(input_media_path: Path, output_path: Path):
+    # get input media duration
+    duration_sec = subprocess.run(["ffprobe", "-i", "file:" + input_media_path.as_posix(), "-show_entries", "format=duration", "-v", "quiet", "-of", "csv=p=0"],
+                                  capture_output=True, text=True).stdout.split("\n")[0].replace("\n", "").replace(" ", "").replace("   ", "").replace("00:", "").replace(":", "").split(".")[0]
+
+    if int(duration_sec) > 240:
+        start_sec = int(duration_sec) - 120
+        end_sec = int(duration_sec) - 60
+    elif int(duration_sec) > 120:
+        start_sec = int(duration_sec) - 80
+        end_sec = int(duration_sec) - 20
+    elif int(duration_sec) > 80:
+        start_sec = int(duration_sec) - 60
+        end_sec = int(duration_sec) - 20
+    else:
+        start_sec = 0
+        end_sec = int(duration_sec)
+
+    # set the FFMpeg command
+    cmd_ffmpeg = ["ffmpeg", "-y", "-ss", f"{start_sec}", "-t", f"{end_sec}",  "-i", "file:" + input_media_path.as_posix(),
+                  "-vn", "-c:a", "pcm_s16le", "-af", "loudnorm", "-ac", "1", "-ar", "16000", "file:" + output_path.as_posix()]
+
+    # run FFmpeg command with a fancy progress bar
+    ff = FfmpegProgress(cmd_ffmpeg)
+    with tqdm(total=100, position=0, ascii="░▒█", desc="Extracting audio", unit="%", unit_scale=True, leave=False, bar_format="{desc} {percentage:3.0f}% | ETA: {remaining} | ⏱: {elapsed}") as pbar:
+        for progress in ff.run_command_with_progress():
+            pbar.update(progress - pbar.n)
+
+
+def add_ffmpeg_escape_chars(string):
+    new_string = ""
+    for char in string:
+        if os.name == 'nt':
+            if char == ":" or char == "\x5c":
+                new_string += "\x5c"
+        new_string += char
+    return new_string

file_utils.py

@@ -0,0 +1,170 @@
+import filecmp
+import os
+import shutil
+import tempfile
+from inspect import currentframe, getframeinfo
+from pathlib import Path
+
+# return the itens in array that is not inexisting or empty
+def validate_files(paths):
+    valid_files = [path for path in paths if file_is_valid(path)]
+    return valid_files
+
+# check if a file is existing and not empty
+def file_is_valid(path):
+    if path is not None and path.is_file():
+        size = path.stat().st_size
+        if size > 0:
+            return True
+    return False
+
+# validate if an string is a valid dir or path with valid content
+def check_valid_path(path_str):
+    # create a Path object from the input string
+    path = Path(path_str)
+
+    # check if the path exists
+    if not path.exists():
+        raise FileNotFoundError(f"The path '{path_str}' does not exist.")
+
+    # check if it's a directory with at least one file or a valid file with content
+    if path.is_dir():
+        # check if the directory has at least one file with content
+        files_with_content = [file for file in path.iterdir() if file.is_file() and file.stat().st_size > 0]
+        if not files_with_content:
+            raise ValueError(f"The directory '{path_str}' does not contain any files with content.")
+    elif path.is_file():
+        # check if the file has content
+        if path.stat().st_size == 0:
+            raise ValueError(f"The file '{path_str}' does not contain any content.")
+    else:
+        raise ValueError(f"The path '{path_str}' is neither a valid directory nor a valid file.")
+
+    return path
+
+# validate if an string is a valid dir or path with valid content
+def check_existing_path(path_str):
+    # create a Path object from the input string
+    path = Path(path_str)
+
+    # check if the path exists
+    if not path.exists():
+        raise FileNotFoundError(f"The path '{path_str}' does not exist.")
+
+    # check if it's a directory with at least one file or a valid file with content
+    if not path.is_dir() and not path.is_file():
+        raise ValueError(f"The path '{path_str}' is neither a valid directory nor a valid file.")
+
+    return path_str
+
+# create a tempfile class to use as object
+class TempFile:
+
+    def __init__(self, final_path: Path, file_ext: str = None):
+        self.final_path: Path = None if final_path is None else Path(
+            final_path)
+        self.file_ext = file_ext
+        os.makedirs(Path(Path(getframeinfo(
+            currentframe()).filename).resolve().parent, "temp"), exist_ok=True)
+        self.temp_file: tempfile.NamedTemporaryFile = tempfile.NamedTemporaryFile(dir=Path(Path(getframeinfo(currentframe()).filename).resolve().parent, "temp"),
+                                                                                  delete=False, suffix=file_ext)
+
+        self.temp_file_name = self.temp_file.name
+        self.temp_file_path: Path = Path(self.temp_file.name)
+
+        self.temp_file.close()
+
+    # return the actual path of the file
+    def getpath(self):
+        if self.temp_file_path.is_file():
+            return self.temp_file_path
+        elif file_is_valid(self.final_path):
+            return self.final_path
+        else:
+            return None
+
+    # return the actual path of the file if not empty
+    def getvalidpath(self):
+        if file_is_valid(self.temp_file_path):
+            return self.temp_file_path
+        elif file_is_valid(self.final_path):
+            return self.final_path
+        else:
+            return None
+
+    # save the temp file into final path
+    def save(self, overwrite_if_valid: bool = True, update_path: Path = None):
+        # update final path case user specifies it
+        if update_path is None:
+            path: Path = self.final_path
+        else:
+            path: Path = update_path
+
+        try:
+            # if file not valid ou overwrite is enabled, move overwiting existing file
+            if not file_is_valid(self.final_path) or overwrite_if_valid:
+                os.makedirs(path.parent, exist_ok=True)
+                shutil.move(self.temp_file_path, path)
+                self.final_path = path
+        except Exception as e:
+            print(f"Error saving file: {e}")
+            return
+
+    # delete the file
+    def destroy(self):
+        try:
+            # destroy temporary file if it exists
+            if file_is_valid(self.temp_file_path):
+                os.remove(self.temp_file_path)
+        except Exception:
+            return
+
+# copy an source file to destination if destination file is not equals to source
+def copy_file_if_different(src_file: Path, dst_file: Path, silent: bool = False):
+    if file_is_valid(dst_file):
+        # Check if destination file exists and is different from source file
+        if filecmp.cmp(src_file, dst_file) and not silent:
+            print(f"{dst_file} already exists and is the same. No need to copy.")
+            return
+
+    os.makedirs(dst_file.parent, exist_ok=True)
+    shutil.copyfile(src_file, dst_file)
+    if not silent:
+        print(f"copied to {dst_file}")
+
+# function to delete dir and all its content using shutil
+def delete_folder(path: Path):
+    if path.is_dir():
+        shutil.rmtree(path)
+
+
+def update_folder_times(folder_path):
+    folder_path = Path(folder_path)
+
+    # Keep track of the newest file's modification time for this folder
+    newest_file_time = None
+
+    for item in folder_path.iterdir():
+        # Check if the item is a file
+        if item.is_file():
+            file_time = item.stat().st_mtime  # Get modification time of the file
+
+            # Update the newest_file_time if it's the first file or if the current file is newer
+            if newest_file_time is None or file_time > newest_file_time:
+                newest_file_time = file_time
+
+        # If the item is a subfolder, recursively update its times and find its newest file time
+        elif item.is_dir():
+            subfolder_newest_time = update_folder_times(item)
+
+            # Update the newest_file_time if a subfolder's newest file is newer
+            if newest_file_time is None or (subfolder_newest_time is not None and subfolder_newest_time > newest_file_time):
+                newest_file_time = subfolder_newest_time
+
+    # Update the folder's modification and creation times with the newest_file_time
+    if newest_file_time is not None:
+        # Convert to an integer (necessary on some systems)
+        newest_file_time = int(newest_file_time)
+        os.utime(path=folder_path, times=(newest_file_time, newest_file_time))
+
+    return newest_file_time  # Return the newest_file_time to update the parent folder's time

header.py

@@ -0,0 +1,16 @@
+badges = """
+<div style="display: flex; justify-content: center;">
+
+<span style="margin-right: 5px"> 
+
+[ ![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white) ](https://github.com/matheusbach/legen)
+
+</span>
+
+</div>
+"""
+
+description = """
+# <center>LeGen</center>
+ <center>Conheça a comunidade no <a href='https://t.me/+Q_Czz4LbbrA0Y2Ux' target='_blank'>Telegram</a></center>
+"""

i18n/config.json

@@ -0,0 +1,14 @@
+{
+  "theme": {
+    "file": "legen.py",
+    "class": "LeGen"
+  },
+  "plugins": [],
+  "discord_presence": false,
+  "lang": {
+    "override": false,
+    "selected_lang": "pt_BR"
+  },
+  "flask_server": false,
+  "version": ""
+}

i18n/i18n.py

@@ -0,0 +1,50 @@
+import os, sys
+import json
+from pathlib import Path
+from locale import getdefaultlocale
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+
+
+class I18nAuto:
+    LANGUAGE_PATH = os.path.join(now_dir, "i18n", "languages")
+
+    def __init__(self, language=None):
+        with open(os.path.join(now_dir, "i18n", "config.json"), "r") as f:
+            config = json.load(f)
+            override = config["lang"]["override"]
+            lang_prefix = config["lang"]["selected_lang"]
+
+        self.language = lang_prefix
+
+        if override == False:
+            language = language or getdefaultlocale()[0]
+            lang_prefix = language[:2] if language is not None else "en"
+            available_languages = self._get_available_languages()
+            matching_languages = [
+                lang for lang in available_languages if lang.startswith(lang_prefix)
+            ]
+            self.language = matching_languages[0] if matching_languages else "en_US"
+
+        self.language_map = self._load_language_list()
+
+    def _load_language_list(self):
+        try:
+            file_path = Path(self.LANGUAGE_PATH) / f"{self.language}.json"
+            with open(file_path, "r", encoding="utf-8") as f:
+                return json.load(f)
+        except FileNotFoundError:
+            raise FileNotFoundError(
+                f"Failed to load language file for {self.language}. Check if the correct .json file exists."
+            )
+
+    def _get_available_languages(self):
+        language_files = [path.stem for path in Path(self.LANGUAGE_PATH).glob("*.json")]
+        return language_files
+
+    def _language_exists(self, language):
+        return (Path(self.LANGUAGE_PATH) / f"{language}.json").exists()
+
+    def __call__(self, key):
+        return self.language_map.get(key, key)

i18n/languages/en_US.json

@@ -0,0 +1,40 @@
+{
+    "Selected folder: ": "Selected folder: ",
+    "No folder selected": "No folder selected",
+    "Select Folder": "Select Folder",
+    "Transcription Engine": "Transcription Engine",
+    "Model": "Model",
+    "Compute Type": "Compute Type",
+    "Device": "Device",
+    "Batch Size": "Batch Size",
+    "Input Language": "Input Language",
+    "Translate to": "Translate to",
+    "Video Codec": "Video Codec",
+    "Audio Codec": "Audio Codec",
+    "Normalize folder times": "Normalize folder times",
+    "Overwrite existing files": "Overwrite existing files",
+    "Copy non-video files": "Copy non-video files",
+    "Disable SRT generation": "Disable SRT generation",
+    "Disable softsubs": "Disable softsubs",
+    "Disable hardsubs": "Disable hardsubs",
+    "Softsubs Output Path": "Softsubs Output Path",
+    "Hardsubs Output Path": "Hardsubs Output Path",
+    "Browse": "Browse",
+    "Run LeGen": "Run LeGen",
+    "Processing stopped by user": "Processing stopped by user",
+    "Please select a folder": "Please select a folder",
+    "Selected folder path does not exist": "Selected folder path does not exist",
+    "legen.py not found in current directory": "legen.py not found in current directory",
+    "Stop LeGen": "Stop LeGen",
+    "Processing...": "Processing...",
+    "Transcription Settings": "Transcription Settings",
+    "Output Settings": "Output Settings",
+    "Options": "Options",
+
+    "gradio": "gradio",
+
+    "Input Path": "Input Path",
+    "Enter path to file or folder": "Enter path to file or folder",
+    "Stop": "Stop"
+
+}

i18n/languages/pt_BR.json

@@ -0,0 +1,39 @@
+{
+    "Selected folder:": "Pasta selecionada:",
+    "No folder selected": "Nenhuma pasta selecionada",
+    "Select Folder": "Selecionar Pasta",
+    "Transcription Engine": "Motor de Transcrição",
+    "Model": "Modelo",
+    "Compute Type": "Tipo de Computação",
+    "Device": "Dispositivo",
+    "Batch Size": "Tamanho do Lote",
+    "Input Language": "Idioma de Entrada",
+    "Translate to": "Traduzir para",
+    "Video Codec": "Codec de Vídeo",
+    "Audio Codec": "Codec de Áudio",
+    "Normalize folder times": "Normalizar tempos da pasta",
+    "Overwrite existing files": "Sobrescrever arquivos existentes",
+    "Copy non-video files": "Copiar arquivos não de vídeo",
+    "Disable SRT generation": "Desabilitar geração de SRT",
+    "Disable softsubs": "Desabilitar softsubs",
+    "Disable hardsubs": "Desabilitar hardsubs",
+    "Softsubs Output Path": "Caminho de Saída das Softsubs",
+    "Hardsubs Output Path": "Caminho de Saída das Hardsubs",
+    "Browse": "Navegar",
+    "Run LeGen": "Executar LeGen",
+    "Processing stopped by user": "Processamento interrompido pelo usuário",
+    "Please select a folder": "Por favor, selecione uma pasta",
+    "Selected folder path does not exist": "Caminho da pasta selecionada não existe",
+    "legen.py not found in current directory": "legen.py não encontrado no diretório atual",
+    "Stop LeGen": "Parar LeGen",
+    "Processing...": "Processando...",
+    "Transcription Settings": "Configurações de Transcrição",
+    "Output Settings": "Configurações de Saída",
+    "Options": "Opções",
+
+    "gradio": "gradio",
+
+    "Input Path": "Caminho de entrada",
+    "Enter path to file or folder": "Digite o caminho para o arquivo ou pasta",
+    "Stop": "Parar"
+}

i18n/scan.py

@@ -0,0 +1,71 @@
+import ast
+import json
+from pathlib import Path
+from collections import OrderedDict
+
+
+def extract_i18n_strings(node):
+    i18n_strings = []
+
+    if (
+        isinstance(node, ast.Call)
+        and isinstance(node.func, ast.Name)
+        and node.func.id == "i18n"
+    ):
+        for arg in node.args:
+            if isinstance(arg, ast.Str):
+                i18n_strings.append(arg.s)
+
+    for child_node in ast.iter_child_nodes(node):
+        i18n_strings.extend(extract_i18n_strings(child_node))
+
+    return i18n_strings
+
+
+def process_file(file_path):
+    with open(file_path, "r") as f:
+        code = f.read()
+        if "I18nAuto" in code:
+            tree = ast.parse(code)
+            i18n_strings = extract_i18n_strings(tree)
+            print(file_path, len(i18n_strings))
+            return i18n_strings
+    return []
+
+
+# Use pathlib for file handling
+py_files = Path(".").rglob("*.py")
+
+# Use a set to store unique strings
+code_keys = set()
+
+for py_file in py_files:
+    strings = process_file(py_file)
+    code_keys.update(strings)
+
+print()
+print("Total unique:", len(code_keys))
+
+standard_file = "languages/en_US.json"
+with open(standard_file, "r", encoding="utf-8") as f:
+    standard_data = json.load(f, object_pairs_hook=OrderedDict)
+standard_keys = set(standard_data.keys())
+
+# Combine unused and missing keys sections
+unused_keys = standard_keys - code_keys
+missing_keys = code_keys - standard_keys
+
+print("Unused keys:", len(unused_keys))
+for unused_key in unused_keys:
+    print("\t", unused_key)
+
+print("Missing keys:", len(missing_keys))
+for missing_key in missing_keys:
+    print("\t", missing_key)
+
+code_keys_dict = OrderedDict((s, s) for s in code_keys)
+
+# Use context manager for writing back to the file
+with open(standard_file, "w", encoding="utf-8") as f:
+    json.dump(code_keys_dict, f, ensure_ascii=False, indent=4, sort_keys=True)
+    f.write("\n")

legen.ipynb

@@ -0,0 +1,227 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "G7E7eZwJ7F5c"
+      },
+      "outputs": [],
+      "source": [
+        "#@title *Prepare* { display-mode: \"form\", run: \"auto\" }\n",
+        "\n",
+        "#@markdown # **Prepare the environment**\n",
+        "#@markdown Execute to install necessary packages, modules, fonts\n",
+        "\n",
+        "#@markdown Mount Google Drive at /content/drive (your drive folder at /content/drive/MyDrive):\n",
+        "mount_gdrive = True #@param {type:\"boolean\"}\n",
+        "#@markdown Force mount again. Useful for bug cases:\n",
+        "force_remount = False #@param {type:\"boolean\"}\n",
+        "\n",
+        "# remove the old log\n",
+        "!rm -rf error_log.txt > /dev/null\n",
+        "\n",
+        "import os\n",
+        "import subprocess\n",
+        "from google.colab import drive\n",
+        "\n",
+        "# mount Google Drive\n",
+        "if mount_gdrive:\n",
+        "    print(\"Mounting your Google Drive | Waiting user Allow Access | \", end='')\n",
+        "    try:\n",
+        "        drive.mount('/content/drive/', force_remount=force_remount)\n",
+        "    except Exception as e:\n",
+        "        print(f\"[✗]: {e}\")\n",
+        "\n",
+        "# update code\n",
+        "print(\"Ensuring the LeGen code is existing and updated...\", end='')\n",
+        "repo_url = \"https://github.com/matheusbach/legen.git\"\n",
+        "local_folder = \"/content/src\"  # LeGen source path\n",
+        "\n",
+        "# Create directory if it does not exist\n",
+        "os.makedirs(local_folder, exist_ok=True)\n",
+        "\n",
+        "# Try git status in the directory\n",
+        "git_task = \"git fetch\"\n",
+        "process = subprocess.Popen(git_task, cwd=local_folder, shell=True)\n",
+        "return_code = process.wait()\n",
+        "if return_code == 0:\n",
+        "  git_task = \"git fetch && git reset --hard origin/main && git pull\"\n",
+        "else:\n",
+        "  !rm -rf local_folder > /dev/null\n",
+        "  os.makedirs(local_folder, exist_ok=True)\n",
+        "  git_task = f\"git clone {repo_url} {local_folder}\"\n",
+        "\n",
+        "# If it is a git repo, fetch, reset, and pull. Else, clone.\n",
+        "with open('/content/error_log.txt', 'a') as f:\n",
+        "    process = subprocess.Popen(git_task, cwd=local_folder, shell=True, stderr=f)\n",
+        "    return_code = process.wait()\n",
+        "    print(\"[✔]\" if return_code == 0 else \"[✗]\")\n",
+        "\n",
+        "# install pip requirements.txt updating\n",
+        "print(\"Installing or updating pip requirements...\", end='')\n",
+        "with open('/content/error_log.txt', 'a') as f:\n",
+        "    process = subprocess.Popen('pip3 install --upgrade $(grep -v \"git+https://github.com/matheusbach/whisperx.git\" requirements.txt | grep -v \"torch\") && pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 && pip3 install git+https://github.com/matheusbach/whisperx.git --upgrade', cwd=local_folder, shell=True, stderr=f)\n",
+        "    return_code = process.wait()\n",
+        "    print(\"[✔]\" if return_code == 0 else \"[✗]\")\n",
+        "\n",
+        "# install ffmpeg and xvfb\n",
+        "print(\"Installing FFmpeg and xvfb...\", end='')\n",
+        "with open('/content/error_log.txt', 'a') as f:\n",
+        "    process = subprocess.Popen('apt update -y ; apt install ffmpeg xvfb -y', shell=True, stderr=f)\n",
+        "    return_code = process.wait()\n",
+        "    print(\"[✔]\" if return_code == 0 else \"[✗]\")\n",
+        "\n",
+        "# install pip requirements.txt updating\n",
+        "print(\"Installing fonts...\", end='')\n",
+        "with open('/content/error_log.txt', 'a') as f:\n",
+        "    process = subprocess.Popen('echo ttf-mscorefonts-installer msttcorefonts/accepted-mscorefonts-eula select true | debconf-set-selections && apt install -y ttf-mscorefonts-installer && fc-cache -f -v', shell=True, stderr=f)\n",
+        "    return_code = process.wait()\n",
+        "    print(\"[✔]\" if return_code == 0 else \"[✗]\")\n",
+        "\n",
+        "# create a virtual display\n",
+        "os.system('Xvfb :1 -screen 0 2560x1440x8  &') # create virtual display with size 1600x1200 and 8 bit color. Color can be changed to 24, 16 or 8\n",
+        "os.environ['DISPLAY'] = ':1.0' # tell X clients to use our virtual DISPLAY :1.0.\n",
+        "\n",
+        "print(\"\\nPreparation tasks done.\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Bz77fHta9JxG"
+      },
+      "outputs": [],
+      "source": [
+        "#@title *Configure* { display-mode: \"form\", run: \"auto\" }\n",
+        "#@markdown # **Define Software Settings**\n",
+        "#@markdown ---\n",
+        "#@markdown ## General Options\n",
+        "#@markdown Set where your files are located (your Drive is the base /content/drive/MyDrive):\n",
+        "import os\n",
+        "from IPython.display import display\n",
+        "import ipywidgets as widgets\n",
+        "input_path = \"/content/drive/MyDrive/LeGen/media\" #@param {type:\"string\"}\n",
+        "#@markdown Set where output soft subs (.srt and embed) videos will be saved on your Drive:\n",
+        "output_softsubs_path = \"/content/drive/MyDrive/LeGen/softsubs\" #@param {type:\"string\"}\n",
+        "#@markdown Set where output hard subs (burned in) videos will be saved on your Drive:\n",
+        "output_hardsubs_path = \"/content/drive/MyDrive/LeGen/hardsubs\" #@param {type:\"string\"}\n",
+        "\n",
+        "#@markdown ---\n",
+        "overwrite = False #@param {type:\"boolean\"}\n",
+        "normalize = False #@param {type:\"boolean\"}\n",
+        "copy_extra_files = True #@param {type:\"boolean\"}\n",
+        "\n",
+        "# generate_srt_files = True #@param {type:\"boolean\"}\n",
+        "generate_softsub = True #@param {type:\"boolean\"}\n",
+        "generate_hardsub = True  # @param {type:\"boolean\"}\n",
+        "\n",
+        "# buttons for directory create\n",
+        "button = widgets.Button(description=\"Create directories!\")\n",
+        "output = widgets.Output()\n",
+        "\n",
+        "\n",
+        "def on_button_clicked(b):\n",
+        "  # Create input and output directories if it does not exist\n",
+        "  os.makedirs(input_path, exist_ok=True)\n",
+        "  if generate_softsub:\n",
+        "    os.makedirs(output_softsubs_path, exist_ok=True)\n",
+        "  if generate_hardsub:\n",
+        "    os.makedirs(output_hardsubs_path, exist_ok=True)\n",
+        "  with output:\n",
+        "    print(\"Done.\")\n",
+        "\n",
+        "\n",
+        "button.on_click(on_button_clicked)\n",
+        "display(button, output)\n",
+        "\n",
+        "#@markdown ---\n",
+        "#@markdown ## Transcription Settings:\n",
+        "transcription_engine = 'WhisperX' # @param [\"Whisper\", \"WhisperX\"]\n",
+        "transcription_device = 'auto' #@param [\"auto\", \"cpu\", \"cuda\"]\n",
+        "transcription_model = 'large' #@param [\"tiny\", \"small\", \"medium\", \"large\", \"large-v1\", \"large-v2\", \"large-v3\"]\n",
+        "compute_type = 'default' # @param [\"default\", \"int8\", \"int16\", \"float16\", \"float32\"]\n",
+        "batch_size = 12 # @param {type: \"number\"}\n",
+        "transcription_input_lang = 'auto detect' #@param [\"auto detect\", \"af\", \"am\", \"ar\", \"as\", \"az\", \"ba\", \"be\", \"bg\", \"bn\", \"bo\", \"br\", \"bs\", \"ca\", \"cs\", \"cy\", \"da\", \"de\", \"el\", \"en\", \"es\", \"et\", \"eu\", \"fa\", \"fi\", \"fo\", \"fr\", \"gl\", \"gu\", \"ha\", \"haw\", \"he\", \"hi\", \"hr\", \"ht\", \"hu\", \"hy\", \"id\", \"is\", \"it\", \"ja\", \"jw\", \"ka\", \"kk\", \"km\", \"kn\", \"ko\", \"la\", \"lb\", \"ln\", \"lo\", \"lt\", \"lv\", \"mg\", \"mi\", \"mk\", \"ml\", \"mn\", \"mr\", \"ms\", \"mt\", \"my\", \"ne\", \"nl\", \"nn\", \"no\", \"oc\", \"pa\", \"pl\", \"ps\", \"pt\", \"ro\", \"ru\", \"sa\", \"sd\", \"si\", \"sk\", \"sl\", \"sn\", \"so\", \"sq\", \"sr\", \"su\", \"sv\", \"sw\", \"ta\", \"te\", \"tg\", \"th\", \"tk\", \"tl\", \"tr\", \"tt\", \"uk\", \"ur\", \"uz\", \"vi\", \"yi\", \"yo\", \"zh\"]\n",
+        "\n",
+        "#@markdown ---\n",
+        "#@markdown ## Translation Settings:\n",
+        "#@markdown Set the destination langrage code. Set to same as original to skip translation\n",
+        "target_language_code = 'pt' #@param [\"af\", \"sq\", \"am\", \"ar\", \"hy\", \"as\", \"ay\", \"az\", \"bm\", \"eu\", \"be\", \"bn\", \"bho\", \"bs\", \"bg\", \"ca\", \"ceb\", \"zh-CN\", \"zh-TW\", \"co\", \"hr\", \"cs\", \"da\", \"dv\", \"doi\", \"nl\", \"en\", \"eo\", \"et\", \"ee\", \"fil\", \"fi\", \"fr\", \"fy\", \"gl\", \"ka\", \"de\", \"el\", \"gn\", \"gu\", \"ht\", \"ha\", \"haw\", \"he\", \"hi\", \"hmn\", \"hu\", \"is\", \"ig\", \"ilo\", \"id\", \"ga\", \"it\", \"ja\", \"jv\", \"kn\", \"kk\", \"km\", \"rw\", \"gom\", \"ko\", \"kri\", \"ku\", \"ckb\", \"ky\", \"lo\", \"la\", \"lv\", \"ln\", \"lt\", \"lg\", \"lb\", \"mk\", \"mai\", \"mg\", \"ms\", \"ml\", \"mt\", \"mi\", \"mr\", \"mni-Mtei\", \"lus\", \"mn\", \"my\", \"ne\", \"no\", \"ny\", \"or\", \"om\", \"ps\", \"fa\", \"pl\", \"pt\", \"pa\", \"qu\", \"ro\", \"ru\", \"sm\", \"sa\", \"gd\", \"nso\", \"sr\", \"st\", \"sn\", \"sd\", \"si\", \"sk\", \"sl\", \"so\", \"es\", \"su\", \"sw\", \"sv\", \"tl\", \"tg\", \"ta\", \"tt\", \"te\", \"th\", \"ti\", \"ts\", \"tr\", \"tk\", \"ak\", \"uk\", \"ur\", \"ug\", \"uz\", \"vi\", \"cy\", \"xh\", \"yi\", \"yo\", \"zu\"]\n",
+        "\n",
+        "#@markdown ---\n",
+        "#@markdown ## Video Settings:\n",
+        "codec_video = \"h264\"  #@param [\"h264\", \"hevc\", \"mpeg4\"]\n",
+        "video_hardware_api = \"auto\"  #@param [\"auto\", \"none\", \"nvenc\", \"vaapi\", \"amf\", \"v4l2m2m\", \"qsv\", \"videotoolbox\", \"cuvid\"]\n",
+        "\n",
+        "codec_audio = \"aac\"  #@param [\"aac\", \"libopus\", \"libmp3lame\", \"pcm_s16le\"]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "n4KSJ9BL7JOs"
+      },
+      "outputs": [],
+      "source": [
+        "#@title *Run* { display-mode: \"form\" }\n",
+        "#@markdown # **Run LeGen.py**\n",
+        "\n",
+        "print(\"Starting LeGen...\")\n",
+        "import torch\n",
+        "try:\n",
+        "    import tensorflow  # required in Colab to avoid protobuf compatibility issues\n",
+        "except ImportError:\n",
+        "    pass\n",
+        "\n",
+        "# Create input and output directories if it does not exist\n",
+        "os.makedirs(input_path, exist_ok=True)\n",
+        "if generate_softsub:\n",
+        "  os.makedirs(output_softsubs_path, exist_ok=True)\n",
+        "if generate_hardsub:\n",
+        "  os.makedirs(output_hardsubs_path, exist_ok=True)\n",
+        "\n",
+        "#build query\n",
+        "query = f\" -i '{input_path}'\"\n",
+        "query += f\" --output_softsubs '{output_softsubs_path}'\"\n",
+        "query += f\" --output_hardsubs '{output_hardsubs_path}'\"\n",
+        "query += \" --overwrite\" if overwrite else \"\"\n",
+        "query += \" --norm\" if normalize else \"\"\n",
+        "query += \" --copy_files\" if not copy_extra_files else \"\"\n",
+        "query += \" --disable_softsubs\" if not generate_softsub else \"\"\n",
+        "query += \" --disable_hardsubs\" if not generate_hardsub else \"\"\n",
+        "query += f\" -ts:e {transcription_engine.lower()}\"\n",
+        "query += f\" -ts:d {transcription_device.lower()}\"\n",
+        "query += f\" -ts:m {transcription_model}\"\n",
+        "query += f\" -ts:c {compute_type}\"\n",
+        "query += f\" -ts:b {batch_size}\"\n",
+        "query += f\" --input_lang {transcription_input_lang}\" if transcription_input_lang != \"auto detect\" else \"\"\n",
+        "query += f\" --translate {target_language_code.lower()}\"\n",
+        "query += f\" -c:v {codec_video}\" + (\"\" if video_hardware_api == \"none\" else f\"_{video_hardware_api}\" if video_hardware_api != \"auto\" else \"_nvenc\" if torch.cuda.is_available() else \"\")\n",
+        "query += f\" -c:a {codec_audio}\"\n",
+        "\n",
+        "#run python script\n",
+        "print(f\"command line: python3 /content/src/legen.py {query}\", end=\"\\n\\n\")\n",
+        "!python3 /content/src/legen.py $query"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "gpuType": "T4",
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

legen.py

@@ -0,0 +1,280 @@
+import argparse
+import os
+import subprocess
+import time
+from inspect import currentframe, getframeinfo
+from pathlib import Path
+
+import ffmpeg_utils
+import file_utils
+import translate_utils
+from utils import time_task, audio_extensions, video_extensions, check_other_extensions
+
+version = "v0.16"
+
+# Terminal colors
+default = "\033[1;0m"
+gray = "\033[1;37m"
+wblue = "\033[1;36m"
+blue = "\033[1;34m"
+yellow = "\033[1;33m"
+green = "\033[1;32m"
+red = "\033[1;31m"
+
+print(f"""
+{blue}888              {gray} .d8888b.                   
+{blue}888              {gray}d88P  Y88b                  
+{blue}888              {gray}888    888                  
+{blue}888      .d88b.  {gray}888         .d88b.  88888b. 
+{blue}888     d8P  Y8b {gray}888  88888 d8P  Y8b 888 "88b
+{blue}888     88888888 {gray}888    888 88888888 888  888
+{blue}888     Y8b.     {gray}Y88b  d88P Y8b.     888  888
+{blue}88888888 "Y8888  {gray} "Y8888P88  "Y8888  888  888
+
+legen {version} - github.com/matheusbach/legen{default}
+python {__import__('sys').version}
+""")
+time.sleep(1.5)
+
+# Define parameters and configurations
+parser = argparse.ArgumentParser(prog="LeGen", description="Uses AI to locally transcribes speech from media files, generating subtitle files, translates the generated subtitles, inserts them into the mp4 container, and burns them directly into video",
+                                 argument_default=True, allow_abbrev=True, add_help=True, usage='LeGen -i INPUT_PATH [other options]')
+parser.add_argument("-i", "--input_path",
+                    help="Path to media files. Can be a folder containing files or an individual file", required=True, type=Path)
+parser.add_argument("--norm", default=False, action="store_true",
+                    help="Normalize folder times and run vidqa on input_path before starting processing files")
+parser.add_argument("-ts:e", "--transcription_engine", type=str, default="whisperx",
+                    help="Transcription engine. Possible values: whisperx (default), whisper")
+parser.add_argument("-ts:m", "--transcription_model", type=str, default="medium",
+                    help="Path or name of the Whisper transcription model. A larger model will consume more resources and be slower, but with better transcription quality. Possible values: tiny, base, small, medium (default), large, ...")
+parser.add_argument("-ts:d", "--transcription_device", type=str, default="auto",
+                    help="Device to run the transcription through Whisper. Possible values: auto (default), cpu, cuda")
+parser.add_argument("-ts:c", "--transcription_compute_type", type=str, default="auto",
+                    help="Quantization for the neural network. Possible values: auto (default), int8, int8_float32, int8_float16, int8_bfloat16, int16, float16, bfloat16, float32")
+parser.add_argument("-ts:b", "--transcription_batch", type=int, default=4,
+                    help="Number of simultaneous segments being transcribed. Higher values will speed up processing. If you have low RAM/VRAM, long duration media files or have buggy subtitles, reduce this value to avoid issues. Only works using transcription_engine whisperx. (default: 4)")
+parser.add_argument("--translate", type=str, default="none",
+                    help="Translate subtitles to language code if not the same as origin. (default: don't translate)")
+parser.add_argument("--input_lang", type=str, default="auto",
+                    help="Indicates (forces) the language of the voice in the input media (default: auto)")
+parser.add_argument("-c:v", "--codec_video", type=str, default="h264", metavar="VIDEO_CODEC",
+                    help="Target video codec. Can be used to set acceleration via GPU or another video API [codec_api], if supported (ffmpeg -encoders). Ex: h264, libx264, h264_vaapi, h264_nvenc, hevc, libx265 hevc_vaapi, hevc_nvenc, hevc_cuvid, hevc_qsv, hevc_amf (default: h264)")
+parser.add_argument("-c:a", "--codec_audio", type=str, default="aac", metavar="AUDIO_CODEC",
+                    help="Target audio codec. (default: aac). Ex: aac, libopus, mp3, vorbis")
+parser.add_argument("-o:s", "--output_softsubs", default=None, type=Path,
+                    help="Path to the folder or output file for the video files with embedded softsub (embedded in the mp4 container and .srt files). (default: softsubs_ + input_path)")
+parser.add_argument("-o:h", "--output_hardsubs", default=None, type=Path,
+                    help="Output folder path for video files with burned-in captions and embedded in the mp4 container. (default: hardsubs_ + input_path)")
+parser.add_argument("--overwrite", default=False, action="store_true",
+                    help="Overwrite existing files in output directories")
+parser.add_argument("--disable_srt", default=False, action="store_true",
+                    help="Disable .srt file generation and don't insert subtitles in mp4 container of output_softsubs")
+parser.add_argument("--disable_softsubs", default=False, action="store_true",
+                    help="Don't insert subtitles in mp4 container of output_softsubs. This option continues generating .srt files")
+parser.add_argument("--disable_hardsubs", default=False, action="store_true",
+                    help="Disable subtitle burn in output_hardsubs")
+parser.add_argument("--copy_files", default=False, action="store_true",
+                    help="Copy other (non-video) files present in input directory to output directories. Only generate the subtitles and videos")
+args = parser.parse_args()
+
+if not args.output_softsubs and not args.input_path.is_file():
+    args.output_softsubs = compatibility_path if (compatibility_path := Path(args.input_path.parent, "legen_srt_" + args.input_path.name)).exists() else Path(args.input_path.parent, "softsubs_" + args.input_path.name)
+if not args.output_hardsubs and not args.input_path.is_file():
+    args.output_hardsubs = compatibility_path if (compatibility_path := Path(args.input_path.parent, "legen_burned_" + args.input_path.name)).exists() else Path(args.input_path.parent, "hardsubs_" + args.input_path.name)
+
+if args.transcription_device == "auto":
+    import torch
+    torch_device = ("cuda" if torch.cuda.is_available() else "cpu")
+else:
+    torch_device = str.lower(args.transcription_device)
+
+transcription_compute_type = args.transcription_compute_type if args.transcription_compute_type != "default" else "float16" if not torch_device == "cpu" else "float32"
+
+args.transcription_model = "large-v3" if args.transcription_model == "large" else args.transcription_model
+
+# ----------------------------------------------------------------------------
+
+if args.norm:
+    # normalize video using vidqa
+    with time_task(message_start=f"Running {wblue}vidqa{default} and updating folder modifiation times in {gray}{args.input_path}{default}", end="\n"):
+        subprocess.run(["vidqa", "-i", args.input_path, "-m", "unique", "-fd",
+                        Path(Path(getframeinfo(currentframe()).filename).resolve().parent, "vidqa_data")])
+        # update folder time structure
+        file_utils.update_folder_times(args.input_path)
+
+# load whisper model
+with time_task(message_start=f"\nLoading {args.transcription_engine} model: {wblue}{args.transcription_model}{default} ({transcription_compute_type}) on {wblue}{torch_device}{default}", end="\n"):
+    if args.transcription_engine == 'whisperx':
+        import whisperx
+        import whisperx_utils
+    
+        whisper_model = whisperx.load_model(
+            whisper_arch=args.transcription_model, device=torch_device, compute_type=transcription_compute_type, asr_options={"repetition_penalty": 1, "prompt_reset_on_temperature": 0.5, "no_repeat_ngram_size": 2,})
+    elif args.transcription_engine == 'whisper':
+        import whisper
+
+        import whisper_utils
+        whisper_model = whisper.load_model(
+            name=args.transcription_model, device=torch_device, in_memory=True)
+    else:
+        raise ValueError(f'Unsupported transcription engine {args.transcription_engine}. Supported values: whisperx, whisper')
+
+with time_task(message="⌛ Processing files for"):
+    path: Path
+    for path in (item for item in sorted(sorted(Path(args.input_path).rglob('*'), key=lambda x: x.stat().st_mtime), key=lambda x: len(x.parts)) if item.is_file()):
+        rel_path = path.relative_to(args.input_path)
+        with time_task(message_start=f"\nProcessing {yellow}{rel_path.as_posix()}{default}", end="\n", message="⌚ Done in"):
+            try:
+                # define file type by extensions
+                if path.suffix.lower() in video_extensions:
+                    file_type = "video"
+                elif path.suffix.lower() in audio_extensions:
+                    file_type = "audio"
+                else:
+                    file_type = "other"
+
+                if file_type == "video" or file_type == "audio":
+                    # define paths
+                    origin_media_path = path
+                    dupe_filename = len(check_other_extensions(path, list(video_extensions | audio_extensions))) > 1
+                    posfix_extension = path.suffix.lower().replace('.', '_') if dupe_filename else ''
+
+                    softsub_video_dir = Path(args.output_softsubs, rel_path.parent)
+                    burned_video_dir = Path(args.output_hardsubs, rel_path.parent)
+                    # output video extension will be changed to .mp4
+                    softsub_video_path = Path(args.output_softsubs, rel_path.stem + posfix_extension + ".mp4")
+                    hardsub_video_path = Path(burned_video_dir, rel_path.stem + posfix_extension + ".mp4")
+                    subtitle_translated_path = Path(
+                        softsub_video_dir, rel_path.stem + posfix_extension + f"_{args.translate}.srt")
+                    subtitles_path = []
+
+                    if args.input_lang == "auto":
+                        # extract audio
+                        audio_short_extracted = file_utils.TempFile(
+                            None, file_ext=".wav")
+                        ffmpeg_utils.extract_short_wav(
+                            origin_media_path, audio_short_extracted.getpath())
+                        # detect language
+                        print("Detecting audio language: ", end='', flush=True)
+                        if args.transcription_engine == 'whisperx':
+                            audio_language = whisperx_utils.detect_language(
+                                whisper_model, audio_short_extracted.getpath())
+                        if args.transcription_engine == 'whisper':
+                            audio_language = whisper_utils.detect_language(
+                                whisper_model, audio_short_extracted.getpath())
+                        print(f"{gray}{audio_language}{default}")
+
+                        audio_short_extracted.destroy()
+                    else:
+                        audio_language = args.input_lang
+                        print(f"Forced input audio language: {gray}{audio_language}{default}")
+                    # set path after get transcribed language
+                    subtitle_transcribed_path = Path(
+                        softsub_video_dir, rel_path.stem + posfix_extension + f"_{audio_language}.srt")
+                    # create temp file for .srt
+                    transcribed_srt_temp = file_utils.TempFile(
+                        subtitle_transcribed_path, file_ext=".srt")
+                    # skip transcription if transcribed srt for this language is existing (without overwrite neabled) or will not be used in LeGen process
+                    if (file_utils.file_is_valid(subtitle_transcribed_path)) or ((args.disable_hardsubs or file_utils.file_is_valid(hardsub_video_path)) and (args.disable_srt or file_utils.file_is_valid(subtitle_transcribed_path))) and not args.overwrite:
+                        print("Transcription is unnecessary. Skipping.")
+                    else:
+                        # extract audio
+                        audio_extracted = file_utils.TempFile(None, file_ext=".wav")
+                        ffmpeg_utils.extract_audio_wav(
+                            origin_media_path, audio_extracted.getpath())
+                        # transcribe saving subtitles to temp .srt file
+                        if args.transcription_engine == 'whisperx':
+                            print(f"{wblue}Transcribing{default} with {gray}WhisperX{default}")
+                            whisperx_utils.transcribe_audio(
+                                whisper_model, audio_extracted.getpath(), transcribed_srt_temp.getpath(), audio_language, device=torch_device, batch_size=args.transcription_batch)
+                        if args.transcription_engine == 'whisper':
+                            print(f"{wblue}Transcribing{default} with {gray}Whisper{default}")
+                            whisper_utils.transcribe_audio(
+                                model=whisper_model, audio_path=audio_extracted.getpath(), srt_path=transcribed_srt_temp.getpath(), lang=audio_language, disable_fp16=False if transcription_compute_type == "float16" or transcription_compute_type == "fp16" else True)
+
+                        audio_extracted.destroy()
+                        # if save .srt is enabled, save it to destination dir, also update path with language code
+                        if not args.disable_srt:
+                            transcribed_srt_temp.save()
+                    subtitles_path.append(transcribed_srt_temp.getvalidpath())
+                    # translate transcribed subtitle using Google Translate if transcribed language is not equals to target
+                    # skip translation if translation has not requested, has equal source and output language, if file is existing (without overwrite neabled) or will not be used in LeGen process
+                    if args.translate == "none":
+                        pass # translation not requested
+                    elif args.translate == audio_language:
+                        print("Translation is unnecessary because input and output language are the same. Skipping.")
+                    elif (args.disable_hardsubs or file_utils.file_is_valid(hardsub_video_path)) and (args.disable_srt or (file_utils.file_is_valid(subtitle_translated_path) and file_utils.file_is_valid(subtitle_transcribed_path) and file_utils.file_is_valid(subtitle_translated_path))) and not args.overwrite:
+                        print("Translation is unnecessary. Skipping.")
+                        subtitles_path.insert(0, subtitle_translated_path)
+                    elif file_utils.file_is_valid(subtitle_translated_path):
+                        print("Translated file found. Skipping translation.")
+                        subtitles_path.insert(0, subtitle_translated_path)
+                    elif transcribed_srt_temp.getvalidpath():
+                        # create the temp .srt translated file
+                        translated_srt_temp = file_utils.TempFile(
+                            subtitle_translated_path, file_ext=".srt")
+
+                        # translating with google translate public API
+                        print(f"{wblue}Translating{default} with {gray}Google Translate{default}")
+                        subs = translate_utils.translate_srt_file(
+                            transcribed_srt_temp.getvalidpath(), translated_srt_temp.getpath(), args.translate)
+                        if not args.disable_srt:
+                            translated_srt_temp.save()
+
+                        subtitles_path.insert(0, translated_srt_temp.getvalidpath())
+                    if not args.disable_softsubs:
+                        if file_utils.file_is_valid(softsub_video_path) and not args.overwrite:
+                            print(f"Existing video file {gray}{softsub_video_path}{default}. Skipping subtitle insert")
+                        else:
+                            # create the temp .mp4 with srt in video container
+                            video_softsubs_temp = file_utils.TempFile(
+                                softsub_video_path, file_ext=".mp4")
+
+                            # insert subtitle into container using ffmpeg
+                            print(f"{wblue}Inserting subtitle{default} in mp4 container using {gray}FFmpeg{default}")
+                            ffmpeg_utils.insert_subtitle(input_media_path=origin_media_path, subtitles_path=subtitles_path,
+                                                        burn_subtitles=False, output_video_path=video_softsubs_temp.getpath(),
+                                                        codec_video=args.codec_video, codec_audio=args.codec_audio)
+                            video_softsubs_temp.save()
+                    if not args.disable_hardsubs:
+                        if file_utils.file_is_valid(hardsub_video_path) and not args.overwrite:
+                            print(f"Existing video file {gray}{hardsub_video_path}{default}. Skipping subtitle burn")
+                        else:
+                            # create the temp .mp4 with srt in video container
+                            video_hardsubs_temp = file_utils.TempFile(
+                                hardsub_video_path, file_ext=".mp4")
+                            # insert subtitle into container and burn using ffmpeg
+                            print(f"{wblue}Inserting subtitle{default} in mp4 container and {wblue}burning{default} using {gray}FFmpeg{default}")
+                            ffmpeg_utils.insert_subtitle(input_media_path=origin_media_path, subtitles_path=subtitles_path,
+                                                        burn_subtitles=True, output_video_path=video_hardsubs_temp.getpath(),
+                                                        codec_video=args.codec_video, codec_audio=args.codec_audio)
+                            video_hardsubs_temp.save()
+                else:
+                    print("not a video file")
+                    if args.copy_files:
+                        if not args.disable_srt:
+                            # copia o arquivo extra para pasta que contém também os arquivos srt
+                            file_utils.copy_file_if_different(path, Path(
+                                args.output_softsubs, rel_path))
+                        if not args.disable_hardsubs:
+                            # copia o arquivo extra para pasta que contém os videos queimados
+                            file_utils.copy_file_if_different(path, Path(
+                                args.output_hardsubs, rel_path))
+            except Exception as e:
+                file = path.as_posix()
+                print(f"{red}ERROR !!!{default} {file}")
+                print(f"{yellow}check legen-errors.txt for details{default}")
+                # extract the relevant information from the exception object
+                current_time = time.strftime("%y/%m/%d %H:%M:%S", time.localtime())
+
+                error_message = f"[{current_time}] {file}: {type(e).__name__}: {str(e)}"
+                # write the error message to a file
+                with open(Path(Path(getframeinfo(currentframe()).filename).resolve().parent, "legen-errors.txt"), "a") as f:
+                    f.write(error_message + "\n")
+                    f.close()
+
+    print("Deleting temp folder")
+    file_utils.delete_folder(
+        Path(Path(getframeinfo(currentframe()).filename).resolve().parent, "temp"))
+
+    print(f"{green}Tasks done!{default}")

pyproject.toml

@@ -0,0 +1,40 @@
+[build-system]
+requires = ["setuptools", "setuptools_scm[toml]>=6.2"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "LeGen"
+authors = [
+    {name = "Matheus Bach"},
+]
+description = "LeGen is a Python script that normalizes video files using vidqa, transcribes subtitles from audio with Whisper, translates generated subtitles using Google Translator, saves subtitles in .srt files, inserts subtitles into .mp4 container and burns subtitles directly onto videos using FFmpeg "
+readme = "README.md"
+requires-python = ">=3.7"
+keywords = ["subtitle", "whisper", "ffmpeg", "translator", "video"]
+license = {text = "GPL 3"}
+classifiers = [
+    "Framework :: LeGen",
+    "Programming Language :: Python :: 3",
+]
+dependencies = [
+    "deep_translator",
+    "ffmpeg_progress_yield",
+    "openai_whisper",
+    "pysrt",
+    "torch",
+    "tqdm",
+    "whisper",
+    "vidqa",
+    "whisperx"
+]
+py_modules = [
+    "translate_utils",
+    "file_utils",
+    "whisper_utils",
+    "whisperx_utils",
+    "ffmpeg_utils"
+]
+dynamic = ["version"]
+
+
+[project.scripts]

requirements.txt

@@ -0,0 +1,11 @@
+deep_translator
+ffmpeg_progress_yield
+openai_whisper
+pysrt
+torch
+tqdm
+whisper
+vidqa
+git+https://github.com/matheusbach/whisperx.git
+flet
+tensorflow

subtitle_utils.py

@@ -0,0 +1,171 @@
+import os
+import re
+import tkinter as tk
+from pathlib import Path
+
+import pysrt
+
+
+def SaveSegmentsToSrt(segments: list, output_path: Path):
+    # Create the subtitle file
+    subs = pysrt.SubRipFile()
+    sub_idx = 1
+
+    for i in range(len(segments)):
+        start_time = segments[i]["start"]
+        end_time = segments[i]["end"]
+        duration = end_time - start_time
+        timestamp = f"{start_time:.3f} - {end_time:.3f}"
+        text = segments[i]["text"]
+
+        sub = pysrt.SubRipItem(index=sub_idx, start=pysrt.SubRipTime(seconds=start_time),
+                               end=pysrt.SubRipTime(seconds=end_time), text=text)
+        subs.append(sub)
+        sub_idx += 1
+
+    # make dir and save .srt
+    os.makedirs(output_path.parent, exist_ok=True)
+    subs.save(output_path)
+
+
+def string_width(text, font_name="Jost", font_size=18):
+    """
+    Determines the width of a string using tkinter.
+    """
+    tries_remaining = 5
+    
+    while (tries_remaining > 0):
+        tries_remaining -= 1
+        try:
+            root = tk.Tk()
+            width = tk.font.Font(name=font_name, size=font_size,
+                                weight="bold").measure(text)
+            root.destroy()
+            return width
+        except Exception:
+            pass
+
+    # all failed, return 60% of height per char
+    return len(text) * font_size * 0.60
+
+
+def is_punctuation_end(word):
+    """Verifica se a palavra termina com uma pontuação."""
+    return any(word.endswith(punct) for punct in ['.', ',', '!', '?', ':', ';'])
+
+
+def split_segments(segments, max_width_px=1440, font_name="Jost", font_size=18):
+    """
+    Split segments based on the max width provided.
+    """
+    new_segments = []
+    for segment in segments:
+        words = segment['words']
+        current_words = []
+        current_width = 0
+
+        for word in words:
+            # Calculate the width with a space after the word
+            added_width = string_width(
+                word['word'] + " ", font_name, font_size)
+            isolated_sentence_ending = is_punctuation_end(word['word']) and not (
+                current_words and is_punctuation_end(current_words[-1]['word']))
+            possible_logical_break_point = len(current_words) >= 2 and len(
+                current_words[-1]['word']) <= 3 and not len(current_words[-2]['word']) <= 3
+
+            if (current_width + added_width < max_width_px) or len(current_words) == 0 or isolated_sentence_ending or possible_logical_break_point:
+                current_words.append(word)
+                current_width += added_width
+            else:
+                new_segments.append({
+                    'text': ' '.join(word['word'] for word in current_words),
+                    'start': next((word['start'] for word in current_words if 'start' in word), segment['start']),
+                    'end': next((word['end'] for word in reversed(current_words) if 'end' in word), segment['end']),
+                    'words': current_words.copy()
+                })
+                current_words = [word]
+                current_width = added_width
+
+        # For any remaining words
+        if current_words:
+            new_segments.append({
+                'text': ' '.join(word['word'] for word in current_words),
+                'start': next((word['start'] for word in current_words if 'start' in word), segment['start']),
+                'end': next((word['end'] for word in reversed(current_words) if 'end' in word), segment['end']),
+                'words': current_words
+            })
+
+    return new_segments
+
+
+def split_string_to_max_lines(text, max_width=720, max_lines=2, font_name="Jost", font_size=18):
+    threshold = max_width * 0.8
+    total_text_width = string_width(text, font_name, font_size)
+
+    if total_text_width <= threshold or max_lines < 2:
+        return [text]
+
+    words = text.split()
+    lines = []
+    current_line_words = []
+    current_line_width = 0
+
+    for i, word in enumerate(words):
+        word_width = string_width(word + ' ', font_name, font_size)
+        isolated_sentence_ending = is_punctuation_end(word) and not (
+            current_line_words and is_punctuation_end(current_line_words[-1]))
+        possible_logical_break_point = len(current_line_words) >= 2 and len(
+            current_line_words[-1]) <= 3 and not len(current_line_words[-2]) <= 3
+
+        if current_line_width + word_width < total_text_width / max_lines or len(current_line_words) == 0 or isolated_sentence_ending or possible_logical_break_point:
+            current_line_words.append(word)
+            current_line_width += word_width
+        else:
+            lines.append(' '.join(current_line_words))
+            current_line_words = [word]
+            current_line_width = word_width
+
+        if len(lines) == max_lines - 1:
+            remaining_words = words[i:]
+            lines.append(' '.join(remaining_words))
+            break
+
+    if current_line_words and len(lines) < max_lines:
+        lines.append(' '.join(current_line_words))
+
+    return lines
+
+
+def adjust_times(segments, extra_end_time=1.0):
+    for i in range(len(segments) - 1):  # We don't need to check the last segment
+        current_end = segments[i]['end']
+        next_start = segments[i + 1]['start']
+
+        gap = next_start - current_end
+
+        # If the gap is more than 1.5 + extra_end_time
+        if gap > 1.5 + extra_end_time:
+            segments[i]['end'] = current_end + extra_end_time
+
+        # If the gap is less than 1.5 + extra_end_time
+        elif gap < 1.5 + extra_end_time:
+            segments[i]['end'] = next_start
+
+    return segments
+
+
+def format_segments(segments: list, max_line_width_px: int = 380, max_lines_per_segment: int = 2):
+    print('Formatting segments...', end='', flush=True)
+
+    segments = split_segments(
+        segments, max_line_width_px * max_lines_per_segment)
+
+    for segment in segments:
+        segment["text"] = "\n".join(split_string_to_max_lines(
+            text=segment["text"], max_width=max_line_width_px, max_lines=max_lines_per_segment))
+
+    segments = adjust_times(segments)
+    
+    print('\r                      ', end='\r', flush=True)
+
+    return segments

translate_utils.py

@@ -0,0 +1,232 @@
+import asyncio
+import os
+from pathlib import Path
+
+import deep_translator
+import pysrt
+import tqdm.asyncio
+import subtitle_utils
+from utils import format_time
+
+# all entence endings for japanese and normal people languages
+sentence_endings = ['.', '!', '?', ')', 'よ', 'ね',
+                    'の', 'さ', 'ぞ', 'な', 'か', '！', '。', '」', '…']
+
+# a good separator is a char or string that doenst change the translation quality but is near ever preserved in result at same or near position
+separator = " ◌ "
+separator_unjoin = separator.replace(' ', '')
+chunk_max_chars = 4999
+
+
+def translate_srt_file(srt_file_path: Path, translated_subtitle_path: Path, target_lang):
+    # Load the original SRT file
+    subs = pysrt.open(srt_file_path, encoding='utf-8')
+
+    # Extract the subtitle content and store it in a list. Also rejoin all lines splited
+    sub_content = [' '.join(sub.text.strip().splitlines()) for sub in subs]
+
+    # Make chunks of at maximum $chunk_max_chars to stay under Google Translate public API limits
+    chunks = join_sentences(sub_content, chunk_max_chars) or []
+
+    # Empty list to store enumerated translated chunks
+    translated_chunks = [None] * len(chunks)
+
+    tasks = []
+    # Limit to 7 concomitant running tasks
+    semaphore = asyncio.Semaphore(7)
+
+    # Async chunks translate function
+    async def translate_async():
+        async def run_translate(index, chunk, lang):
+            while True:
+                try:
+                    async with semaphore:
+                        result = await asyncio.wait_for(translate_chunk(index, chunk, lang), 120)
+                    translated_chunks[index] = result
+                    break
+                except Exception:
+                    # Restart task
+                    await asyncio.sleep(3)
+
+        for index, chunk in enumerate(chunks):
+            task = asyncio.create_task(
+                run_translate(index, chunk, target_lang))
+            tasks.append(task)
+
+        for tsk in tqdm.asyncio.tqdm_asyncio.as_completed(tasks, total=len(tasks), desc="Translating", unit="chunks", unit_scale=False, leave=True, bar_format="{desc} {percentage:3.0f}% | {n_fmt}/{total_fmt} | ETA: {remaining} | ⏱: {elapsed}"):
+            await tsk
+
+    # Cria um loop de eventos e executa as tasks
+    loop = asyncio.get_event_loop()
+    loop.run_until_complete(translate_async())
+
+    print('Processing translation...', end='')
+
+    # Unjoin lines within each chunk that end with a sentence ending
+    unjoined_texts = [unjoin_sentences(
+        chunk, translated_chunks[i], separator_unjoin) or "" for i, chunk in enumerate(chunks)]
+    unjoined_texts = [text for sublist in unjoined_texts for text in sublist]
+
+    # Split lines as necessary targeting same number of lines as original string
+    for i, segment in enumerate(unjoined_texts):
+        unjoined_texts[i] = "\n".join(subtitle_utils.split_string_to_max_lines(
+            text=segment, max_width=0, max_lines=len(subs[i].text.splitlines())))
+
+    # Combine the original and translated subtitle content
+    for i, sub in enumerate(subs):
+        sub.text = unjoined_texts[i]
+
+    # Save the translated SRT file
+    os.makedirs(translated_subtitle_path.parent, exist_ok=True)
+    subs.save(translated_subtitle_path, encoding='utf-8')
+
+    print('\r                         ', end='\r')
+
+    return subs
+
+# Async chunk translate function
+
+
+async def translate_chunk(index, chunk, target_lang):
+    while True:
+        try:
+            # Translate the subtitle content of the chunk using Google Translate
+            translator = deep_translator.google.GoogleTranslator(
+                source='auto', target=target_lang)
+            translated_chunk: str = await asyncio.wait_for(asyncio.get_event_loop().run_in_executor(None, translator.translate, chunk), 30)
+            await asyncio.sleep(0)
+
+            # if nothing is retuned, return the original chunk
+            if translated_chunk is None or len(translated_chunk.replace(separator.strip(), '').split()) == 0:
+                return chunk
+
+            return translated_chunk
+        except Exception as e:
+            # If an error occurred, retry
+            del translator
+            print(
+                f"\r[chunk {index}]: Exception: {e.__doc__} Retrying in 30 seconds...", flush=True)
+            await asyncio.sleep(30)
+
+
+def join_sentences(lines, max_chars):
+    """
+    Joins the given list of strings in a way that each part ends with a sentence ending.
+    Adds a separator to all lines in the chunk.
+    """
+    joined_lines = []
+    current_chunk = ""
+
+    for line in lines:
+        if not line or line is None:
+            line = 'ㅤ'  # invisible char (not a simple space)
+
+        if len(current_chunk) + len(line) + len(separator) <= max_chars:
+            current_chunk += line + separator
+            if any(line.endswith(ending) for ending in sentence_endings):
+                joined_lines.append(current_chunk)
+                current_chunk = ""
+        else:
+            if current_chunk:
+                joined_lines.append(current_chunk)
+                current_chunk = ""
+            if len(current_chunk) + len(line) + len(separator) <= max_chars:
+                current_chunk += line + separator
+            else:
+                # if a single line exceed max_chars, use maximum posible number of words. Discart the remaining
+                end_index = line.rfind(
+                    ' ', 0, max_chars - (1 + len(separator)))
+
+                if end_index == - (1 + len(separator)):
+                    end_index = max_chars - (1 + len(separator))
+
+                joined_lines.append(
+                    (line[:end_index] + '…' + separator)[:max_chars])
+
+    # append a chunk wich doenst have a formal end with sentence endings
+    if current_chunk:
+        joined_lines.append(current_chunk)
+
+    return joined_lines
+
+
+def unjoin_sentences(original_sentence: str, modified_sentence: str, separator: str):
+    """
+    Splits the original and modified sentences into lines based on the separator.
+    Tries to match the number of lines between the original and modified sentences.
+    """
+
+    if original_sentence is None:
+        return ' '
+
+    # split by separator, remove double spaces and empty or only space strings from list
+    original_lines = original_sentence.split(separator)
+    original_lines = [s.strip().replace('  ', ' ').lstrip(" ,.:;)") if s.strip().replace('  ', ' ').lstrip(" ,.:;)") else s
+                      for s in original_lines if s.strip()]
+    original_lines = [s for s in original_lines if s]
+    original_lines = [s for s in original_lines if s.strip()]
+
+    if modified_sentence is None:
+        return original_lines or ' '
+
+    # fix strange formatation returned by google translate, case occuring
+    modified_sentence.replace(f"{separator_unjoin} ", f"{separator_unjoin}").replace(f" {separator_unjoin}", f"{separator_unjoin}").replace(
+        f"{separator_unjoin}.", f".{separator_unjoin}").replace(f"{separator_unjoin},", f",{separator_unjoin}")
+
+    # split by separator, remove double spaces and empty or only space strings from list
+    modified_lines = modified_sentence.split(separator_unjoin)
+    modified_lines = [s.strip().replace('  ', ' ').lstrip(" ,.:;)") if s.strip().replace('  ', ' ').lstrip(" ,.:;)") else s
+                      for s in modified_lines if s.strip()]
+    modified_lines = [s for s in modified_lines if s]
+    modified_lines = [s for s in modified_lines if s.strip()]
+
+    # if original lines is "silence" sign, doenst translate
+    if original_lines == "..." or original_lines == "…":
+        return original_lines
+
+    # all ok, return lines
+    if len(original_lines) == len(modified_lines):
+        return modified_lines
+
+    # zero words? return original sentence, removing separator
+    original_word_count = sum(len(line.strip().split())
+                              for line in original_lines)
+    modified_word_count = len(' '.join(modified_lines).strip().split())
+    if original_word_count == 0 or modified_word_count == 0:
+        return original_sentence.replace(separator, ' ').replace('  ', ' ')
+
+    # calculate proportion of words between original and translated
+    modified_words_proportion = modified_word_count / original_word_count
+    # list all modified words
+    modified_words = ' '.join(modified_lines).replace(separator, "").replace(
+        separator_unjoin, "").replace("  ", " ").strip().split(' ')
+
+    new_modified_lines = []
+    current_index = 0
+
+    # reconstruct lines based on proportion of original and translated words
+    for i in range(len(original_lines)):
+        # Calculate the number of words for the current modified sentence
+        num_words = int(
+            round(len(original_lines[i].strip().split()) * modified_words_proportion))
+
+        # Extract words from modified list
+        generated_line = ' '.join(
+            modified_words[current_index:current_index+num_words])
+
+        # Update the current index
+        current_index += num_words
+
+        # append remaining if is the last loop
+        if i == len(original_lines) - 1:
+            ' '.join([generated_line, ' '.join(
+                modified_words[current_index:])])
+
+        # Add modified sentence to the new list
+        new_modified_lines.append(generated_line.replace("  ", " ").strip())
+
+    # case it continues being shorter
+    while len(new_modified_lines) < len(original_lines):
+        new_modified_lines.append(new_modified_lines[-1])
+
+    return new_modified_lines or original_lines or ' '

ui.py

@@ -0,0 +1,558 @@
+import flet as ft
+import os
+from pathlib import Path
+import subprocess
+from typing import Optional
+import asyncio
+import threading
+import sys
+import os
+import sys
+from i18n.i18n import I18nAuto
+i18n = I18nAuto()
+
+# Força o uso de UTF-8 para o Python
+os.environ["PYTHONIOENCODING"] = "utf-8"
+
+# Para garantir que a codificação esteja correta no terminal
+if sys.platform == "win32":
+    # No Windows, podemos forçar a codificação UTF-8 no console
+    os.system('chcp 65001')
+
+# Redefine a configuração de codificação da saída padrão
+sys.stdout.reconfigure(encoding='utf-8')
+sys.stderr.reconfigure(encoding='utf-8')
+
+import re
+
+def clean_ansi(text: str) -> str:
+    """Remove códigos ANSI e limpa o texto para exibição no Flet"""
+    ansi_escape = re.compile(r'\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])')
+    return ansi_escape.sub('', text)
+
+
+def process_output(line: str) -> str:
+    """Processa uma linha de saída, limpando-a apenas para exibição no Flet"""
+    clean_line = clean_ansi(line.strip())
+    
+    # Verifica por padrões de progresso
+    if "%" in clean_line:
+        try:
+            # Extrai o número do progresso
+            progress_match = re.search(r'(\d+\.?\d*)%', clean_line)
+            if progress_match:
+                progress_value = float(progress_match.group(1)) / 100
+                return clean_line, progress_value
+        except ValueError:
+            pass
+    
+    return clean_line, None
+
+
+
+class LeGenUI:
+    def __init__(self):
+        self.input_path: Optional[Path] = None
+        self.selected_file_text: Optional[ft.Text] = None
+        self.dark_mode = True
+        self.progress = None
+        self.progress_text = None
+        self.page = None
+        self.processing = False
+        self.current_process = None
+        self.run_button = None
+    
+    def create_credits_dialog(self):
+        async def close_dialog(e):
+            self.credits_dialog.open = False
+            await self.page.update_async()
+            
+        async def open_url(e, url):
+            await self.page.launch_url_async(url)
+
+        return ft.AlertDialog(
+            modal=True,
+            title=ft.Text("Créditos", size=20, weight=ft.FontWeight.BOLD),
+            content=ft.Column([
+                ft.Text("LeGen - Legendas Generator", weight=ft.FontWeight.BOLD),
+                ft.Text("Desenvolvido com ❤️ pela comunidade"),
+                ft.Text(""),
+                ft.Text("Desenvolvedores:", weight=ft.FontWeight.BOLD),
+                ft.Text("• Matheus bach"),
+                ft.Text("• UI por Rafa.Godoy"),
+                ft.Text("• Colaboradores do GitHub"),
+                ft.Text(""),
+                ft.Text("Links:", weight=ft.FontWeight.BOLD),
+                ft.TextButton(
+                    "GitHub",
+                    icon=ft.icons.CODE,
+                    on_click=lambda e: self.page.launch_url("https://github.com/matheusbach/legen")
+                ),
+                ft.TextButton(
+                    "Telegram",
+                    icon=ft.icons.TELEGRAM,
+                    on_click=lambda e: self.page.launch_url("https://t.me/+Q_Czz4LbbrA0Y2Ux")
+                ),
+                ft.Text(""),
+                ft.Text("Tecnologias:", weight=ft.FontWeight.BOLD),
+                ft.Text("• Python"),
+                ft.Text("• WhisperX/Whisper"),
+                ft.Text("• FFmpeg"),
+                ft.Text("• Flet UI Framework"),
+            ], tight=True),
+            actions=[
+                ft.TextButton("Fechar", on_click=close_dialog),
+            ],
+            actions_alignment=ft.MainAxisAlignment.END,
+        )
+        
+    def main(self, page: ft.Page):
+        self.page = page
+        page.title = "LeGen UI"
+        page.padding = 20
+        page.theme_mode = ft.ThemeMode.DARK if self.dark_mode else ft.ThemeMode.LIGHT
+        page.window.min_width = 1280
+        page.window.min_height = 720
+        page.scroll = ft.ScrollMode.AUTO
+        
+        def toggle_dark_mode(e):
+            self.dark_mode = not self.dark_mode
+            page.theme_mode = ft.ThemeMode.DARK if self.dark_mode else ft.ThemeMode.LIGHT
+            page.update()
+        
+        async def show_credits(e):
+            self.credits_dialog = self.create_credits_dialog()
+            self.page.dialog = self.credits_dialog
+            self.credits_dialog.open = True
+            await self.page.update_async()
+
+        async def pick_folder_result(e: ft.FilePickerResultEvent):
+            if e.path:
+                self.input_path = Path(e.path)
+                self.selected_file_text.value = f"{i18n('Selected folder:')} {self.input_path}"
+                await page.update_async()
+
+        async def pick_output_softsubs_result(e: ft.FilePickerResultEvent):
+            if e.path:
+                output_softsubs_path.value = e.path
+                await page.update_async()
+
+        async def pick_output_hardsubs_result(e: ft.FilePickerResultEvent):
+            if e.path:
+                output_hardsubs_path.value = e.path
+                await page.update_async()
+
+        #file_picker = ft.FilePicker(on_result=pick_file_result)
+        folder_picker = ft.FilePicker(on_result=pick_folder_result)
+        softsubs_folder_picker = ft.FilePicker(on_result=pick_output_softsubs_result)
+        hardsubs_folder_picker = ft.FilePicker(on_result=pick_output_hardsubs_result)
+        
+        page.overlay.extend([folder_picker, softsubs_folder_picker, hardsubs_folder_picker])
+                      
+        self.selected_file_text = ft.Text(i18n("No folder selected"))
+        
+        input_section = ft.Container(
+            content=ft.Column([
+                ft.Row([
+                    ft.ElevatedButton(i18n("Select Folder"), on_click=lambda _: folder_picker.get_directory_path()),
+                ]),
+                self.selected_file_text,
+            ]),
+            padding=10,
+        )
+
+        transcription_engines = ["whisperx", "whisper"]
+        transcription_models = ["tiny", "base", "small", "medium", "large", "large-v1", "large-v2", "large-v3", "large-v3-turbo"]
+        compute_types = ["auto", "int8", "float16", "float32"]
+        devices = ["auto", "cpu", "cuda"]
+        languages = ["auto", "en", "es", "pt", "fr", "de", "it", "ja", "ko", "zh"]
+        video_codecs = ["h264", "libx264", "h264_vaapi", "h264_nvenc", "hevc", "libx265", "hevc_vaapi"]
+        audio_codecs = ["aac", "libopus", "mp3", "vorbis"]
+
+        transcription_engine = ft.Dropdown(
+            label=i18n("Transcription Engine"),
+            options=[ft.dropdown.Option(e) for e in transcription_engines],
+            value="whisperx",
+            expand=1
+        )
+
+        transcription_model = ft.Dropdown(
+            label=i18n("Model"),
+            options=[ft.dropdown.Option(m) for m in transcription_models],
+            value="medium",
+            expand=1
+        )
+
+        compute_type = ft.Dropdown(
+            label=i18n("Compute Type"),
+            options=[ft.dropdown.Option(t) for t in compute_types],
+            value="auto",
+            expand=1
+        )
+
+        device = ft.Dropdown(
+            label=i18n("Device"),
+            options=[ft.dropdown.Option(d) for d in devices],
+            value="auto",
+            expand=1
+        )
+
+        batch_size = ft.TextField(
+            label=i18n("Batch Size"),
+            value="4",
+            expand=1,
+            input_filter=ft.NumbersOnlyInputFilter()
+        )
+
+        input_lang = ft.Dropdown(
+            label=i18n("Input Language"),
+            options=[ft.dropdown.Option(l) for l in languages],
+            value="auto",
+            expand=1
+        )
+
+        translate_lang = ft.Dropdown(
+            label=i18n("Translate to"),
+            options=[ft.dropdown.Option(l) for l in languages],
+            value="none",
+            expand=1
+        )
+
+        video_codec = ft.Dropdown(
+            label=i18n("Video Codec"),
+            options=[ft.dropdown.Option(c) for c in video_codecs],
+            value="h264",
+            expand=1
+        )
+
+        audio_codec = ft.Dropdown(
+            label=i18n("Audio Codec"),
+            options=[ft.dropdown.Option(c) for c in audio_codecs],
+            value="aac",
+            expand=1
+        )
+
+        normalize = ft.Checkbox(label=i18n("Normalize folder times"), value=False)
+        overwrite = ft.Checkbox(label=i18n("Overwrite existing files"), value=False)
+        copy_files = ft.Checkbox(label=i18n("Copy non-video files"), value=False)
+        disable_srt = ft.Checkbox(label=i18n("Disable SRT generation"), value=False)
+        disable_softsubs = ft.Checkbox(label=i18n("Disable softsubs"), value=False)
+        disable_hardsubs = ft.Checkbox(label=i18n("Disable hardsubs"), value=False)
+
+        output_softsubs_path = ft.TextField(
+            label=i18n("Softsubs Output Path"),
+            value="softsubs_output",
+            expand=1
+        )
+        output_hardsubs_path = ft.TextField(
+            label=i18n("Hardsubs Output Path"),
+            value="hardsubs_output",
+            expand=1
+        )
+
+        output_paths = ft.Container(
+            content=ft.Column([
+                ft.Row([
+                    output_softsubs_path,
+                    ft.ElevatedButton(i18n("Browse"), on_click=lambda _: softsubs_folder_picker.get_directory_path()),
+                ]),
+                ft.Row([
+                    output_hardsubs_path,
+                    ft.ElevatedButton(i18n("Browse"), on_click=lambda _: hardsubs_folder_picker.get_directory_path()),
+                ]),
+            ]),
+            padding=10,
+        )
+
+        async def show_alert(msg: str, color: str = "error"):
+            banner = ft.Banner(
+                bgcolor=color,
+                leading=ft.Icon(ft.icons.WARNING_AMBER_ROUNDED if color == "error" else ft.icons.INFO),
+                content=ft.Text(msg),
+                actions=[
+                    ft.TextButton("Ok", on_click=lambda _: self.page.overlay.remove(banner)),
+                ],
+            )
+            self.page.overlay.append(banner)
+            await page.update_async()
+        
+        async def stop_processing():
+            if self.current_process:
+                self.current_process.terminate()
+                self.current_process = None
+                self.processing = False
+                self.run_button.text = i18n("Run LeGen")
+                await page.update_async()
+                await show_alert(i18n("Processing stopped by user"), "info")
+                await update_progress(False)
+
+        async def update_progress(visible: bool, progress: float = 0):
+            self.progress.visible = visible
+            self.progress_text.visible = visible
+            if visible:
+                self.progress.value = progress
+            await page.update_async()
+
+            
+        async def update_ui(text):
+            if not self.progress_text:
+                return
+            self.progress_text.value = text
+            await page.update_async()
+
+
+        import locale
+
+        def process_in_thread(cmd):
+            print(f"Executing command: {' '.join(cmd)}")
+
+            loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(loop)
+
+            try:
+                self.current_process = subprocess.Popen(
+                    cmd,
+                    stdout=subprocess.PIPE,
+                    stderr=subprocess.PIPE,  # Redireciona stderr também
+                    text=True,
+                    encoding='utf-8',
+                    bufsize=1,  # Linha a linha
+                    universal_newlines=True
+                )
+
+
+                
+
+                async def read_output():
+                    final_message = None  # Variável para armazenar a mensagem final
+                    while True:
+                        if self.current_process is None:
+                            break
+                        
+                        # Leitura de stdout
+                        output = self.current_process.stdout.readline()
+                        if output:
+                            print(f"{output.strip()}")
+                            #print(f"Process output (with ANSI): {output.strip()}")
+                            clean_line, progress_value = process_output(output.strip())
+
+                            # Verifica se a mensagem final está presente e armazena
+                            if "⌛ Processing files for" in clean_line:
+                                final_message = clean_line  # Armazena a mensagem final
+
+                            await update_ui(clean_line)
+                            if progress_value is not None:
+                                await update_progress(True, progress_value)
+
+                        # Leitura de stderr (para capturar possíveis erros do FFmpeg)
+                        error_output = self.current_process.stderr.readline()
+                        if error_output:
+                            #print(f"Process error: {error_output.strip()}")  # Exibe stderr no terminal
+                            clean_line, _ = process_output(error_output.strip())
+                            await update_ui(clean_line)
+                        
+                        # Verifica se o processo terminou
+                        if output == '' and error_output == '' and self.current_process.poll() is not None:
+                            break
+
+                    # Após a conclusão, exibe a mensagem final, se ela existir
+                    if final_message:
+                        await update_ui(final_message)
+
+
+
+
+
+
+                loop.run_until_complete(read_output())
+
+                if self.current_process:
+                    returncode = self.current_process.poll()
+                    if returncode is None:
+                        self.current_process.terminate()
+                        self.current_process.wait()
+
+                    stdout, stderr = self.current_process.communicate()
+
+                    loop.run_until_complete(update_progress(False))
+
+                    if returncode == 0:
+                        loop.run_until_complete(show_alert("Processing completed successfully!", "success"))
+                    else:
+                        print(f"Process error: {stderr}")
+                        loop.run_until_complete(show_alert(f"Error: {stderr}"))
+
+            except Exception as e:
+                print(f"Exception occurred: {str(e)}")
+                loop.run_until_complete(update_progress(False))
+                loop.run_until_complete(show_alert(f"Error: {str(e)}"))
+
+            finally:
+                loop.close()
+                async def reset_ui():
+                    self.processing = False
+                    self.run_button.text = "Run LeGen"
+                    await page.update_async()
+                loop.run_until_complete(reset_ui())
+                
+        async def _reset_button():
+            self.processing = False
+            self.run_button.text = "Run LeGen"
+            await self.page.update_async()
+                
+        async def run_legen(e):
+            if self.processing:
+                await stop_processing()
+                return
+
+            if not self.input_path:
+                await show_alert(i18n("Please select a folder"))
+                return
+
+            if not os.path.exists(str(self.input_path)):
+                await show_alert(i18n("Selected folder path does not exist"))
+                return
+
+            if not os.path.exists("legen.py"):
+                await show_alert(i18n("legen.py not found in current directory"))
+                return
+
+            cmd = ["python", "legen.py", "-i", str(self.input_path)]
+
+            if normalize.value:
+                cmd.append("--norm")
+            if overwrite.value:
+                cmd.append("--overwrite")
+            if copy_files.value:
+                cmd.append("--copy_files")
+            if disable_srt.value:
+                cmd.append("--disable_srt")
+            if disable_softsubs.value:
+                cmd.append("--disable_softsubs")
+            if disable_hardsubs.value:
+                cmd.append("--disable_hardsubs")
+
+            cmd.extend(["-ts:e", transcription_engine.value])
+            cmd.extend(["-ts:m", transcription_model.value])
+            cmd.extend(["-ts:d", device.value])
+            cmd.extend(["-ts:c", compute_type.value])
+            cmd.extend(["-ts:b", batch_size.value])
+
+            if translate_lang.value != "none":
+                cmd.extend(["--translate", translate_lang.value])
+            if input_lang.value != "auto":
+                cmd.extend(["--input_lang", input_lang.value])
+
+            cmd.extend(["-c:v", video_codec.value])
+            cmd.extend(["-c:a", audio_codec.value])
+
+            if output_softsubs_path.value:
+                cmd.extend(["-o:s", output_softsubs_path.value])
+            if output_hardsubs_path.value:
+                cmd.extend(["-o:h", output_hardsubs_path.value])
+
+            self.processing = True
+            self.run_button.text = i18n("Stop LeGen")
+            self.page.update()
+
+            try:
+                await update_progress(True, 0)
+                await asyncio.get_event_loop().run_in_executor(None, process_in_thread, cmd)
+            except Exception as e:
+                #print(f"Error during execution: {str(e)}")
+                await show_alert(f"Error during execution: {str(e)}")
+            finally:
+                self.processing = False
+                self.run_button.text = i18n("Run LeGen")
+                await update_progress(False)
+                #await page.update_async()  # Ocultar a barra de progresso após a conclusão
+
+            # Você pode adicionar um alerta ou mensagem final aqui se necessário
+            await show_alert("Processing has finished.", "info")
+            
+
+        # A seção do layout pode ficar inalterada a menos que você precise de alterações.
+        # Progress bar configuration
+        self.progress = ft.ProgressBar(width=400, color="blue", visible=False, value=0)
+        self.progress_text = ft.Text(i18n("Processing..."), visible=False)
+
+        progress_section = ft.Container(
+            content=ft.Column([
+                self.progress,
+                self.progress_text,
+            ])
+        )
+        
+        self.run_button = ft.ElevatedButton(i18n("Run LeGen"), on_click=run_legen, width=200)
+
+        content = ft.Container(
+            content=ft.Column([
+                ft.Row([
+                    ft.Text("LeGen UI", size=30, weight=ft.FontWeight.BOLD),
+                    ft.Row([
+                        ft.ElevatedButton(
+                            "Créditos",
+                            on_click=show_credits,
+                            icon=ft.icons.INFO
+                        ),
+                        ft.IconButton(
+                            icon=ft.icons.DARK_MODE if not self.dark_mode else ft.icons.LIGHT_MODE,
+                            on_click=toggle_dark_mode,
+                        ),
+                    ]),
+                ], alignment=ft.MainAxisAlignment.SPACE_BETWEEN),
+                input_section,
+                ft.Divider(),
+                ft.Text(i18n("Transcription Settings"), size=20, weight=ft.FontWeight.BOLD),
+                ft.ResponsiveRow([
+                    ft.Column([transcription_engine], col=6),
+                    ft.Column([transcription_model], col=6),
+                ]),
+                ft.ResponsiveRow([
+                    ft.Column([compute_type], col=6),
+                    ft.Column([device], col=6),
+                ]),
+                ft.ResponsiveRow([
+                    ft.Column([batch_size], col=6),
+                    ft.Column([input_lang], col=6),
+                ]),
+                ft.ResponsiveRow([
+                    ft.Column([translate_lang], col=6),
+                ]),
+                ft.Divider(),
+                ft.Text(i18n("Output Settings"), size=20, weight=ft.FontWeight.BOLD),
+                ft.ResponsiveRow([
+                    ft.Column([video_codec], col=6),
+                    ft.Column([audio_codec], col=6),
+                ]),
+                output_paths,
+                ft.Divider(),
+                ft.Text(i18n("Options"), size=20, weight=ft.FontWeight.BOLD),
+                ft.ResponsiveRow([
+                    ft.Column([normalize], col=4),
+                    ft.Column([overwrite], col=4),
+                    ft.Column([copy_files], col=4),
+                ]),
+                ft.ResponsiveRow([
+                    ft.Column([disable_srt], col=4),
+                    ft.Column([disable_softsubs], col=4),
+                    ft.Column([disable_hardsubs], col=4),
+                ]),
+                ft.Divider(),
+                progress_section,
+                ft.ElevatedButton(i18n("Run LeGen"), on_click=run_legen, width=200),
+            ]),
+            padding=20
+        )
+
+        # Add content to a scrollable container
+        page.add(
+            ft.Container(
+                content=content,
+                expand=True,
+            )
+        )
+
+if __name__ == '__main__':
+    app = LeGenUI()
+    ft.app(target=app.main)

utils.py

@@ -0,0 +1,72 @@
+import time
+from pathlib import Path
+
+from contextlib import contextmanager
+
+
+@contextmanager
+def time_task(message_start=None, end=' ', message="⏱ Took"):
+    if message_start:
+        print(message_start, end=end, flush=True)
+    start_time = time.time()
+    yield
+    end_time = time.time()
+    elapsed_time = end_time - start_time
+    formatted_elapsed_time = format_time(elapsed_time)
+    print(f"{message} {formatted_elapsed_time}", flush=True)
+
+
+def format_time(elapsed_time):
+    hours, rem = divmod(elapsed_time, 3600)
+    minutes, seconds = divmod(rem, 60)
+
+    # Check and format the non-zero time units
+    parts = []
+    if hours:
+        parts.append(f"{int(hours)}h")
+    if minutes:
+        parts.append(f"{int(minutes)}m")
+    if seconds or not parts:
+        # Add seconds if it's the only non-zero unit or if all units are zero
+        parts.append(f"{int(seconds)}s")
+
+    return ' '.join(parts)
+
+
+def time_func(func):
+    def wrapper(*args, **kwargs):
+        start_time = time.time()
+        result = func(*args, **kwargs)
+        end_time = time.time()
+        elapsed_time = end_time - start_time
+        formatted_elapsed_time = format_time(elapsed_time)
+        print(f"Execution time of {func.__name__}: {formatted_elapsed_time}")
+        return result
+    return wrapper
+
+def check_other_extensions(file_path, extensions_to_check):
+    """
+    Check the existence of files with the same name but different extensions
+    in the same folder.
+
+    Parameters:
+    - file_path (str): The path of the file to check.
+    - extensions_to_check (list): List of extensions to check.
+
+    Returns:
+    - list: List of existing file paths with different extensions.
+    """
+    file_path = Path(file_path)
+    folder = file_path.parent
+    base_name = file_path.stem
+
+    matching_files = [
+        folder / (base_name + ext)
+        for ext in extensions_to_check
+        if (folder / (base_name + ext)).exists()
+    ]
+
+    return matching_files
+
+video_extensions = {".mp4", ".webm", ".mkv", ".avi", ".mov", ".wmv", ".flv", ".vob", ".mts", ".m2ts", ".ts", ".yuv", ".mpg", ".mp2", ".mpeg", ".mpe", ".mpv", ".m2v", ".m4v", ".3gp", ".3g2", ".nsv", ".mts"}
+audio_extensions = {".aa", ".aac", ".aax", ".act", ".aiff", ".alac", ".amr", ".ape", ".au", ".awb", ".dss", ".dvf", ".flac", ".gsm", ".iklax", ".ivs", ".m4a", ".m4b", ".m4p", ".mpga", ".mmf", ".mp3", ".mpc", ".msv", ".nmf", ".ogg", ".oga", ".mogg", ".opus", ".ra", ".rm", ".raw", ".rf64", ".sln", ".tta", ".voc", ".vox", ".wav", ".wma", ".wv", ".webm", ".8svx"}

whisper_utils.py

@@ -0,0 +1,50 @@
+import os
+from pathlib import Path
+
+import pysrt
+import whisper
+import whisper.transcribe
+import whisperx
+import subtitle_utils
+from utils import time_task
+
+
+def transcribe_audio(model: whisper.model, audio_path: Path, srt_path: Path, lang: str = None, disable_fp16: bool = False):
+    # Load audio
+    audio = whisper.load_audio(file=audio_path.as_posix())
+    
+    # Transcribe
+    with time_task():
+        transcribe = model.transcribe(audio=audio, language=lang, fp16=False if disable_fp16 else True, verbose=False)
+
+    # Align if possible
+    if lang in whisperx.alignment.DEFAULT_ALIGN_MODELS_HF or lang in whisperx.alignment.DEFAULT_ALIGN_MODELS_TORCH:
+        with time_task(message_start="Running alignment..."):
+            try:
+                model_a, metadata = whisperx.load_align_model(language_code=lang, device="cuda")
+                transcribe = whisperx.align(transcript=transcribe["segments"], model=model_a, align_model_metadata=metadata, audio=audio, device="cuda", return_char_alignments=True)
+            except Exception:
+                model_a, metadata = whisperx.load_align_model(language_code=lang, device="cpu")  # force load on cpu due errors on gpu
+                transcribe = whisperx.align(transcript=transcribe["segments"], model=model_a, align_model_metadata=metadata, audio=audio, device="cpu", return_char_alignments=True)
+    else:
+        print(f"Language {lang} not suported for alignment. Skipping this step")
+
+    # Format subtitles
+    segments = subtitle_utils.format_segments(transcribe['segments'])
+
+    # Save the subtitle file
+    subtitle_utils.SaveSegmentsToSrt(segments, srt_path)
+
+    return transcribe
+
+
+def detect_language(model: str, audio_path: Path):
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(audio_path.as_posix())
+    audio = whisper.pad_or_trim(audio)
+    # make log-Mel spectrogram and move to the same device as the model
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+
+    # detect the spoken language
+    _, probs = model.detect_language(mel)
+    return max(probs, key=probs.get)

whisperx_utils.py

@@ -0,0 +1,79 @@
+import os
+from pathlib import Path
+
+import whisperx
+import whisper # only for detect language
+
+import whisper_utils
+import subtitle_utils
+from utils import time_task
+
+def transcribe_audio(model: whisperx.asr.WhisperModel, audio_path: Path, srt_path: Path, lang: str = None, device: str = "cpu", batch_size: int = 4):
+    audio = whisperx.load_audio(file=audio_path.as_posix(), sr=model.model.feature_extractor.sampling_rate)
+        
+    # Define the progress callback function
+    def progress_callback(state, current: int = None, total: int = None):
+        args = state, current, total
+        args = [arg for arg in args if arg is not None]
+
+        if len(args) == 1:
+            state = args[0]
+        if len(args) > 1:
+            total = args[-1]
+            current = args[-2]
+            state = None
+        if len(args) > 2:
+            state = args[-3]
+
+        try:
+            if state is None:
+                state = "WhisperX"  
+            elif type(state) == 'String' or type(state) == int:
+                state = state
+            else:
+                state = state.value
+        except:
+            state = "WhisperX"
+
+        print('\r                                                            \r' + state + ((': ' + str(round(current/total*100)) + '%') if current and total else '') + ((' [' + str(current) + '/' + str(total) + ']') if current and total else ''), end=' ', flush=True)
+
+    # Transcribe
+    with time_task("Running WhisperX transcription engine...", end='\n'):
+        transcribe = model.transcribe(audio=audio, language=lang, batch_size=batch_size, on_progress=progress_callback)
+
+    # Align if possible
+    if lang in whisperx.alignment.DEFAULT_ALIGN_MODELS_HF or lang in whisperx.alignment.DEFAULT_ALIGN_MODELS_TORCH:
+        with time_task(message_start="Running alignment...", end='\n'):
+            try:
+                model_a, metadata = whisperx.load_align_model(language_code=lang, device="cuda")
+                transcribe = whisperx.align(transcript=transcribe["segments"], model=model_a, align_model_metadata=metadata, audio=audio, device="cuda", return_char_alignments=True, on_progress=progress_callback)
+            except Exception:
+                model_a, metadata = whisperx.load_align_model(language_code=lang, device="cpu")  # force load on cpu due errors on gpu
+                transcribe = whisperx.align(transcript=transcribe["segments"], model=model_a, align_model_metadata=metadata, audio=audio, device="cpu", return_char_alignments=True, on_progress=progress_callback)
+    else:
+        print(f"Language {lang} not suported for alignment. Skipping this step")
+
+    # Format subtitles
+    segments = subtitle_utils.format_segments(transcribe['segments'])
+
+    # Save the subtitle file
+    subtitle_utils.SaveSegmentsToSrt(segments, srt_path)
+
+    return transcribe
+
+
+def detect_language(model: whisperx.asr.WhisperModel, audio_path: Path):
+    try:
+        if os.getenv("COLAB_RELEASE_TAG"):
+            raise Exception("Method invalid for Google Colab") 
+        audio = whisperx.load_audio(audio_path.as_posix(), model.model.feature_extractor.sampling_rate)
+        audio = whisper.pad_or_trim(audio, model.model.feature_extractor.n_samples)
+        mel = whisperx.asr.log_mel_spectrogram(audio, n_mels=model.model.model.n_mels)
+        encoder_output = model.model.encode(mel)
+        results = model.model.model.detect_language(encoder_output)
+        language_token, language_probability = results[0][0]
+        return language_token[2:-2]
+    except:
+        print("using whisper base model for detection: ", end='')
+        whisper_model = whisper.load_model("base", device="cpu", in_memory=True)
+        return whisper_utils.detect_language(model=whisper_model, audio_path=audio_path)