update2

models/abi/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d49b59265a0a5f5d899dde745c21bc0a492f68f3769521d238b23a446f93b2
+size 145496039

models/abi/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/abi/vocab.txt

@@ -0,0 +1,53 @@
+ɔ
+ê
+ǒ
+ 
+̂
+h
+ě
+i
+ɩ
+k
+á
+̌
+ǐ
+b
+p
+í
+ǔ
+u
+ń
+w
+'
+ί
+f
+ó
+y
+s
+î
+m
+ɛ
+έ
+e
+ʋ
+ḿ
+n
+ú
+o
+d
+â
+ô
+c
+ǎ
+é
+́
+j
+l
+-
+t
+_
+r
+g
+ε
+û
+a

models/abp/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a87c726778281f406b80e0383b53e80f0a39fd75f3dba8c50ab17df25b97c76
+size 145480667

models/abp/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/abp/vocab.txt

@@ -0,0 +1,33 @@
+_
+t
+e
+b
+ō
+j
+c
+r
+f
+w
+i
+q
+h
+g
+l
+m
+k
+y
+d
+ā
+s
+'
+a
+n
+x
+6
+o
+-
+p
+u
+ 
+v
+z

models/aca/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6e02c38c06f326322663ec0e415aaaee53427226be1df1b3fa0ba91ebd6134
+size 145482239

models/aca/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/aca/vocab.txt

@@ -0,0 +1,35 @@
+a
+|
+i
+n
+á
+c
+e
+u
+l
+r
+w
+j
+s
+í
+m
+é
+o
+'
+h
+t
+y
+b
+d
+ú
+q
+ó
+p
+—
+g
+f
+z
+v
+x
+ñ
+ 

models/acd/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ffad2d099b4fbfe8b434922abb825e898b105276f5e18bdc794513400f9203
+size 145476854

models/acd/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/acd/vocab.txt

@@ -0,0 +1,28 @@
+|
+a
+ɛ
+n
+ɔ
+i
+o
+m
+y
+e
+u
+g
+s
+k
+b
+r
+l
+d
+w
+f
+-
+t
+p
+'
+ŋ
+h
+c
+ 

models/ace/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b520bb31ef5f6fe27b350d1cdfafc5e0e7241fc2235c0e0ffd0d2232184892
+size 145487623

models/ace/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/ace/vocab.txt

@@ -0,0 +1,42 @@
+|
+a
+n
+e
+u
+g
+t
+h
+i
+k
+m
+b
+o
+y
+l
+r
+s
+p
+j
+d
+é
+w
+ô
+ë
+-
+c
+ö
+á
+ó
+f
+z
+'
+q
+ú
+`
+0
+6
+4
+3
+1
+2
+ 

models/acf/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77a841ab67ccc15b895c9fb24779b94d85b83e5267992dba49a66bcd6923f93
+size 145480679

models/acf/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/acf/vocab.txt

@@ -0,0 +1,33 @@
+|
+a
+n
+é
+i
+o
+s
+t
+k
+y
+p
+l
+w
+m
+è
+u
+d
+-
+e
+b
+v
+j
+ò
+z
+f
+ʼ
+h
+g
+c
+r
+—
+'
+ 

models/ach/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cffe85baf83584a9876299052071c35e4604a5192b9ecd6402a88d70a6d7a1
+size 145476861

models/ach/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/ach/vocab.txt

@@ -0,0 +1,28 @@
+|
+o
+a
+i
+e
+k
+n
+m
+w
+t
+u
+y
+l
+c
+d
+b
+g
+r
+p
+ŋ
+j
+-
+s
+'
+v
+f
+h
+ 

models/acn/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:650c7c63e516d2c2c363fdc4f9ce8ac58f6b8c37c75fe1a1e4bbe1d633e8e8f0
+size 145483865

models/acn/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/acn/vocab.txt

@@ -0,0 +1,37 @@
+u
+k
+g
+a
+_
+—
+d
+w
+i
+o
+-
+b
+e
+n
+t
+y
+p
+s
+z
+x
+m
+h
+c
+ 
+l
+0
+2
+j
+f
+3
+5
+q
+v
+r
+6
+1
+4

models/acr/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe163f49adbb77ba29f6a49a80ed6417f00de3ed26fc7bde862ef44fbb7bb706
+size 145483857

models/acr/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/acr/vocab.txt

@@ -0,0 +1,37 @@
+|
+a
+i
+'
+k
+r
+u
+e
+j
+n
+o
+c
+l
+h
+t
+q
+w
+x
+m
+b
+s
+y
+p
+z
+d
+—
+ú
+g
+á
+é
+ó
+f
+í
+v
+-
+ñ
+ 

models/acu/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73f60dc370d4b9603a8b4f49a39f38b9ba104cc4873804e37a3742f669656bf
+size 145482199

models/acu/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/acu/vocab.txt

@@ -0,0 +1,35 @@
+a
+|
+i
+n
+u
+t
+r
+m
+k
+s
+e
+h
+j
+c
+w
+y
+p
+g
+o
+í
+—
+ú
+d
+l
+é
+á
+b
+f
+v
+ó
+z
+q
+x
+ñ
+ 

models/ade/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15657ac66a20bbf85a3ff8968ac2f5f1306fe124dbf7557c9ebb35f63db43d7
+size 145486083

models/ade/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/ade/vocab.txt

@@ -0,0 +1,40 @@
+|
+a
+â
+n
+e
+b
+g
+æ
+i
+t
+w
+ô
+y
+k
+o
+r
+l
+u
+d
+m
+f
+s
+û
+p
+à
+-
+è
+ã
+õ
+ù
+î
+å
+ì
+ü
+ǹ
+ò
+h
+'
+c
+ 

models/adh/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04406c957a29e5e62b97e3b528868d11cafbec74886e242d56f8b3501a40bebf
+size 145477721

models/adh/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/adh/vocab.txt

@@ -0,0 +1,29 @@
+|
+o
+i
+a
+e
+n
+k
+m
+w
+r
+y
+h
+t
+d
+j
+g
+u
+l
+p
+c
+b
+ŋ
+s
+f
+'
+z
+v
+-
+ 

models/adj/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256854868625effe7ef0801e3467e22e74986dc465dc3af39f5ee138ffa009a0
+size 145490681

models/adj/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/adj/vocab.txt

@@ -0,0 +1,46 @@
+|
+a
+e
+ɛ
+n
+m
+l
+k
+i
+ŋ
+'
+s
+b
+o
+y
+w
+ɔ
+u
+r
+g
+c
+t
+d
+j
+f
+p
+-
+ó
+́
+í
+̀
+á
+h
+é
+ì
+ò
+ú
+à
+ê
+v
+ù
+̂
+è
+z
+ô
+ 

models/adx/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62192b382120334b39670d3ae5567159358eb66361588f1b42e6cce52b825e83
+size 145500761

models/adx/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/adx/vocab.txt

@@ -0,0 +1,59 @@
+ཤ
+ྐ
+ི
+འ
+ཞ
+ 
+ྩ
+པ
+ྫ
+ྱ
+ྭ
+ཙ
+ད
+ཁ
+ྔ
+ྷ
+ུ
+ེ
+ོ
+_
+ྡ
+ཆ
+མ
+ྟ
+ྤ
+ན
+ཉ
+ཛ
+ཊ
+ཏ
+ྦ
+ྨ
+ང
+ཪ
+ཟ
+ས
+ཚ
+ྣ
+ླ
+ཇ
+ྗ
+ཨ
+ྙ
+ྒ
+བ
+ཅ
+ཧ
+ྲ
+ཝ
+ཡ
+ཱ
+ག
+ཀ
+ར
+ཐ
+ཕ
+ྕ
+ལ
+་

models/aeu/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d9b805eb84438ab960cb51ee261fdaf62280f1b1c0ec27449692ecc857ff8f
+size 145474559

models/aeu/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/aeu/vocab.txt

@@ -0,0 +1,25 @@
+b
+j
+g
+t
+u
+-
+k
+q
+s
+i
+e
+l
+o
+p
+_
+y
+n
+c
+v
+ 
+m
+h
+d
+a
+w

models/agd/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3724c7877b954ab715ef920ca771336f4e3cf1e7596db81cbd11893f035588c
+size 145478407

models/agd/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

models/agd/vocab.txt

@@ -0,0 +1,30 @@
+3
+p
+y
+f
+ó
+4
+0
+á
+m
+-
+r
+h
+ 
+t
+d
+o
+é
+'
+s
+b
+e
+n
+u
+_
+v
+ú
+í
+a
+i
+k

models/agg/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8aa1936c08d0178a46cc741a42e231732c4955096833c58371b5fd4ceefe678
+size 145480667

models/agg/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}