generate html files

.gitignore

@@ -0,0 +1,2 @@
+__pycache__
+*.html

build-generate-subtitles.py

@@ -0,0 +1,223 @@
+#!/usr/bin/env python3
+import os
+import re
+from pathlib import Path
+from typing import List
+from version import min_major, min_minor, min_patch
+
+BASE_URL = "https://huggingface.co/csukuangfj/sherpa-onnx-bin/resolve/main/"
+
+from dataclasses import dataclass
+
+
+@dataclass
+class APP:
+    major: int
+    minor: int
+    patch: int
+    os: str
+    arch: str
+    short_name: str
+
+    def __init__(self, s):
+        # sherpa-onnx-1.10.21-generate-subtitles-macos-arm64-paraformer_small_2024_03_09-zh_en.app.tar.bz2
+
+        s = str(s).split("/")[-1]
+        split = s.split("-")
+        self.major, self.minor, self.patch = list(map(int, split[2].split(".")))
+        self.os = split[5]
+        self.arch = split[6]
+        self.lang = split[8]
+        self.short_name = split[7]
+
+
+def sort_by_app(x):
+    x = APP(x)
+    return (x.major, x.minor, x.patch, x.os, x.arch, x.short_name, x.lang)
+
+
+def get_all_files(d_list: List[str], suffix: str) -> List[str]:
+    if isinstance(d_list, str):
+        d_list = [d_list]
+
+    ss = []
+    for d in d_list:
+        for root, _, files in os.walk(d):
+            for f in files:
+                if f.endswith(suffix):
+                    major, minor, patch = list(map(int, f.split("-")[2].split(".")))
+                    if major >= min_major and minor >= min_minor and patch >= min_patch:
+                        ss.append(os.path.join(root, f))
+
+    ans = sorted(ss, key=sort_by_app, reverse=True)
+
+    return list(map(lambda x: BASE_URL + str(x), ans))
+
+
+def to_file(filename: str, files: List[str]):
+    content = r"""
+<h1> APPs for generating subtitles (生成字幕) </h1>
+This page lists the APPs for <strong>generating subtitles</strong> using <a href="http://github.com/k2-fsa/sherpa-onnx">sherpa-onnx</a>,
+one of the deployment frameworks of <a href="https://github.com/k2-fsa">the Next-gen Kaldi project</a>.
+<br/>
+The name of an APP has the following rule:
+<ul>
+ <li> sherpa-onnx-{version}-generate-subtitles-{os}-{arch}-{model}-{lang}
+</ul>
+where
+<ul>
+ <li> version: It specifies the current version, e.g., 1.10.21
+ <li> os: maocs, windows, linux,
+ <li> arch: The architecture targeted by this APP, e.g., x64, arm64
+ <li> model: The name of the model used in the APP, e.g.,
+      <a href="https://arxiv.org/abs/2310.11230">Zipformer</a>,
+      <a href="https://github.com/openai/whisper">Whisper</a>,
+      <a href="https://github.com/modelscope/FunASR">Paraformer</a>,
+      <a href="https://github.com/FunAudioLLM/SenseVoice">SenseVoice</a>
+ <li> lang: The lang of the model used in the APP, e.g., en for English, zh for Chinese, ja for Japanese, ko for Korean
+</ul>
+
+<br/>
+<br/>
+
+You can download all supported models from
+<a href="https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models">https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models</a>
+
+<br/>
+<br/>
+
+<strong>Note about the license</strong> The code of Next-gen Kaldi is using
+<a href="https://www.apache.org/licenses/LICENSE-2.0">Apache-2.0 license</a>. However,
+we support models from different frameworks. Please check the license of your selected model.
+
+<br/>
+<br/>
+
+<!--
+see https://www.tablesgenerator.com/html_tables#
+-->
+
+<style type="text/css">
+.tg  {border-collapse:collapse;border-spacing:0;}
+.tg td{border-color:black;border-style:solid;border-width:1px;font-family:Arial, sans-serif;font-size:14px;
+  overflow:hidden;padding:10px 5px;word-break:normal;}
+.tg th{border-color:black;border-style:solid;border-width:1px;font-family:Arial, sans-serif;font-size:14px;
+  font-weight:normal;overflow:hidden;padding:10px 5px;word-break:normal;}
+.tg .tg-0pky{border-color:inherit;text-align:left;vertical-align:top}
+.tg .tg-0lax{text-align:left;vertical-align:top}
+</style>
+<table class="tg">
+<thead>
+  <tr>
+    <th class="tg-0pky">APP</th>
+    <th class="tg-0lax">Comment</th>
+    <th class="tg-0pky">ASR Model</th>
+    <th class="tg-0pky">VAD Model</th>
+  </tr>
+</thead>
+<tbody>
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-generate-subtitles-windows-x64-<strong>zipformer_reazonspeech</strong>_2024_08_01-ja</td>
+    <td class="tg-0lax">It supports only <strong>Japanese</strong> (日语). Please refer to the <a href="https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-transducer/zipformer-transducer-models.html#sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01-japanese">doc</a> for more details.</td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.tar.bz2">sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.tar.bz2</td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx">silero_vad.onnx</a></td>
+  </tr>
+
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-generate-subtitles-windows-x64-<strong>zipformer_gigaspeech2</strong>-th</td>
+    <td class="tg-0lax">It supports only <strong>Thai</strong> (泰语). Please refer to the <a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.tar.bz2">doc</a> for more details.</td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-thai-2024-06-20.tar.bz2
+">sherpa-onnx-zipformer-thai-2024-06-20.tar.bz2</td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx">silero_vad.onnx</a></td>
+  </tr>
+
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-generate-subtitles-windows-x64-<strong>whisper_tiny.en</strong>-en</td>
+    <td class="tg-0lax">It supports only <strong>English</strong> (英语). Please see the <a href="https://k2-fsa.github.io/sherpa/onnx/pretrained_models/whisper/tiny.en.html">doc</a> for more details. Whereas we are using tiny.en here, you are free to switch to other kinds of models, e.g., <a href="https://k2-fsa.github.io/sherpa/onnx/pretrained_models/whisper/export-onnx.html#available-models">base</a>.</td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-whisper-tiny.en.tar.bz2">sherpa-onnx-whisper-tiny.en</a></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx">silero_vad.onnx</a></td>
+  </tr>
+
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-generate-subtitles-windows-x64-<strong>sense_voice</strong>-zh_en_ko_ja_yue</td>
+    <td class="tg-0lax"><span style="font-weight:400;font-style:normal">It supports
+      <strong>Chinese, English, Korean, Japense, Cantonese</strong> (中文、英语、韩语、日语、粤语供 5 种语言). Please refer to the
+      <a href="https://k2-fsa.github.io/sherpa/onnx/sense-voice/index.html">doc</a> for more details.</span></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2">sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2</a></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx">silero_vad.onnx</a></td>
+  </tr>
+
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-generate-subtitles-windows-x64-<strong>paraformer_2023_09_14-</strong>-zh_en</td>
+    <td class="tg-0lax"><span style="font-weight:400;font-style:normal">It supports
+      <strong>Chinese and English</strong> （中英双语). Please refer to the
+      <a href="https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-paraformer/paraformer-models.html#csukuangfj-sherpa-onnx-paraformer-zh-2023-09-14-chinese-english">doc</a> for more details.</span></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2">sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2</a></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx">silero_vad.onnx</a></td>
+  </tr>
+
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-generate-subtitles-windows-x64-<strong>zipformer_wenetspeech</strong>-zh</td>
+    <td class="tg-0lax"><span style="font-weight:400;font-style:normal">It supports only <strong>Chinese</strong> (中文). Please
+      refer to the <a href="https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-transducer/zipformer-transducer-models.html#pkufool-icefall-asr-zipformer-wenetspeech-20230615-chinese">doc</a> for more details.</span></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/icefall-asr-zipformer-wenetspeech-20230615.tar.bz2">icefall-asr-zipformer-wenetspeech-20230615.tar.bz2</a></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx">silero_vad.onnx</a></td>
+  </tr>
+
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-generate-subtitles-windows-x64-<strong>zipformer_gigaspeech</strong>-zh</td>
+    <td class="tg-0lax"><span style="font-weight:400;font-style:normal">It supports only <strong>English</strong> (英语). Please
+      refer to the <a href="https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-transducer/zipformer-transducer-models.html#sherpa-onnx-zipformer-gigaspeech-2023-12-12-english">doc</a> for more details.</span></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-gigaspeech-2023-12-12.tar.bz2">sherpa-onnx-zipformer-gigaspeech-2023-12-12.tar.bz2</a></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx">silero_vad.onnx</a></td>
+  </tr>
+
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-generate-subtitles-windows-x64-<strong>paraformer_small_2024_03_09</strong>-zh_en</td>
+    <td class="tg-0lax"><span style="font-weight:400;font-style:normal">It supports <strong>Chinese and English</strong> (中英双语). Please
+      refer to the <a href="https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-paraformer/paraformer-models.html#csukuangfj-sherpa-onnx-paraformer-zh-small-2024-03-09-chinese-english">doc</a> for more details. It uses a small Paraformer model.</span></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-paraformer-zh-small-2024-03-09.tar.bz2">sherpa-onnx-paraformer-zh-small-2024-03-09.tar.bz2</a></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx">silero_vad.onnx</a></td>
+  </tr>
+</tbody>
+</table>
+
+<br/>
+<br/>
+
+<div/>
+    """
+    if "-cn" not in filename:
+        content += """
+        For Chinese users, please <a href="./download-generated-subtitles-cn.html">visit this address</a>,
+        which replaces <a href="huggingface.co">huggingface.co</a> with <a href="hf-mirror.com">hf-mirror.com</a>
+        <br/>
+        <br/>
+        中国用户, 请访问<a href="./download-generated-subtitles-cn.html">这个地址</a>
+        <br/>
+        <br/>
+        """
+
+    with open(filename, "w") as f:
+        print(content, file=f)
+        for x in files:
+            name = x.rsplit("/", maxsplit=1)[-1]
+            print(f'<a href="{x}" />{name}<br/>', file=f)
+
+
+def main():
+    app = get_all_files("generate-subtitles", suffix=".tar.bz2")
+    to_file("./download-generated-subtitles.html", app)
+
+    # for Chinese users
+    app2 = []
+    for a in app:
+        a = a.replace("huggingface.co", "hf-mirror.com")
+        a = a.replace("resolve", "blob")
+        app2.append(a)
+
+    to_file("./download-generated-subtitles-cn.html", app2)
+
+
+if __name__ == "__main__":
+    main()

version.py

@@ -0,0 +1,3 @@
+min_major = 1
+min_minor = 9
+min_patch = 10