Hugging Face's logo

audo
/
seamless-m4t-v2-large

Text-to-Speech
Safetensors
96 languages
seamless_communication
seamless_m4t_v2
automatic-speech-recognition
audio-to-audio
Model card Files Community
1
camenduru commited on
Commit
63245ce
•
1 Parent(s): 9f1b62a

thanks to facebook ❤

Browse files
Files changed (17) hide show
  1. README.md +336 -0
  2. added_tokens.json +100 -0
  3. config.json +117 -0
  4. generation_config.json +0 -0
  5. m4t_v2_multitask_unity2.pt +3 -0
  6. model-00001-of-00002.safetensors +3 -0
  7. model-00002-of-00002.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
  9. preprocessor_config.json +111 -0
  10. seamlessM4T_v2_large.pt +3 -0
  11. seamlessm4t_arch.svg +1088 -0
  12. sentencepiece.bpe.model +3 -0
  13. special_tokens_map.json +144 -0
  14. spm_char_lang38_tc.model +3 -0
  15. tokenizer.model +3 -0
  16. tokenizer_config.json +933 -0
  17. vocoder_v2.pt +3 -0
README.md ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ language:
4
+ - af
5
+ - am
6
+ - ar
7
+ - as
8
+ - az
9
+ - be
10
+ - bn
11
+ - bs
12
+ - bg
13
+ - ca
14
+ - cs
15
+ - zh
16
+ - cy
17
+ - da
18
+ - de
19
+ - el
20
+ - en
21
+ - et
22
+ - fi
23
+ - fr
24
+ - or
25
+ - om
26
+ - ga
27
+ - gl
28
+ - gu
29
+ - ha
30
+ - he
31
+ - hi
32
+ - hr
33
+ - hu
34
+ - hy
35
+ - ig
36
+ - id
37
+ - is
38
+ - it
39
+ - jv
40
+ - ja
41
+ - kn
42
+ - ka
43
+ - kk
44
+ - mn
45
+ - km
46
+ - ky
47
+ - ko
48
+ - lo
49
+ - ln
50
+ - lt
51
+ - lb
52
+ - lg
53
+ - lv
54
+ - ml
55
+ - mr
56
+ - mk
57
+ - mt
58
+ - mi
59
+ - my
60
+ - nl
61
+ - nb
62
+ - ne
63
+ - ny
64
+ - oc
65
+ - pa
66
+ - ps
67
+ - fa
68
+ - pl
69
+ - pt
70
+ - ro
71
+ - ru
72
+ - sk
73
+ - sl
74
+ - sn
75
+ - sd
76
+ - so
77
+ - es
78
+ - sr
79
+ - sv
80
+ - sw
81
+ - ta
82
+ - te
83
+ - tg
84
+ - tl
85
+ - th
86
+ - tr
87
+ - uk
88
+ - ur
89
+ - uz
90
+ - vi
91
+ - wo
92
+ - xh
93
+ - yo
94
+ - ms
95
+ - zu
96
+ - ary
97
+ - arz
98
+ - yue
99
+ - kea
100
+ metrics:
101
+ - bleu
102
+ - wer
103
+ - chrf
104
+ inference: False
105
+ tags:
106
+ - automatic-speech-recognition
107
+ - audio-to-audio
108
+ - text-to-speech
109
+ library_name: seamless_communication
110
+ ---
111
+
112
+ # SeamlessM4T v2
113
+
114
+ **SeamlessM4T** is our foundational all-in-one **M**assively **M**ultilingual and **M**ultimodal **M**achine **T**ranslation model delivering high-quality translation for speech and text in nearly 100 languages.
115
+
116
+ SeamlessM4T models support the tasks of:
117
+ - Speech-to-speech translation (S2ST)
118
+ - Speech-to-text translation (S2TT)
119
+ - Text-to-speech translation (T2ST)
120
+ - Text-to-text translation (T2TT)
121
+ - Automatic speech recognition (ASR).
122
+
123
+ SeamlessM4T models support:
124
+ - 🎤 101 languages for speech input.
125
+ - 💬 96 Languages for text input/output.
126
+ - 🔊 35 languages for speech output.
127
+
128
+ 🌟 We are releasing SeamlessM4T v2, an updated version with our novel *UnitY2* architecture.
129
+ This new model improves over SeamlessM4T v1 in quality as well as inference speed in speech generation tasks.
130
+
131
+ The v2 version of SeamlessM4T is a multitask adaptation of our novel *UnitY2* architecture.
132
+ *Unity2* with its hierarchical character-to-unit upsampling and non-autoregressive text-to-unit decoding considerably improves over SeamlessM4T v1 in quality and inference speed.
133
+
134
+ **SeamlessM4T v2 is also supported by 🤗 Transformers, more on it [in the dedicated section below](#transformers-usage).**
135
+
136
+ ![SeamlessM4T architectures](seamlessm4t_arch.svg)
137
+
138
+ ## SeamlessM4T models
139
+ | Model Name | #params | checkpoint | metrics |
140
+ | ------------------ | ------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
141
+ | [SeamlessM4T-Large v2](https://huggingface.co/facebook/seamless-m4t-v2-large) | 2.3B | [checkpoint](https://huggingface.co/facebook/seamless-m4t-v2-large/blob/main/seamlessM4T_v2_large.pt) | [metrics](https://dl.fbaipublicfiles.com/seamless/metrics/seamlessM4T_large_v2.zip) |
142
+ | [SeamlessM4T-Large (v1)](https://huggingface.co/facebook/seamless-m4t-large) | 2.3B | [checkpoint](https://huggingface.co/facebook/seamless-m4t-large/blob/main/multitask_unity_large.pt) | [metrics](https://dl.fbaipublicfiles.com/seamless/metrics/seamlessM4T_large.zip) |
143
+ | [SeamlessM4T-Medium (v1)](https://huggingface.co/facebook/seamless-m4t-medium) | 1.2B | [checkpoint](https://huggingface.co/facebook/seamless-m4t-medium/blob/main/multitask_unity_medium.pt) | [metrics](https://dl.fbaipublicfiles.com/seamless/metrics/seamlessM4T_medium.zip) |
144
+
145
+ We provide the extensive evaluation results of seamlessM4T-Large and SeamlessM4T-Medium reported in the paper (as averages) in the `metrics` files above.
146
+
147
+ The evaluation data ids for FLEURS, CoVoST2 and CVSS-C can be found [here](https://dl.fbaipublicfiles.com/seamless/metrics/evaluation_data_ids.zip)
148
+
149
+
150
+ ## Evaluating SeamlessM4T models
151
+ To reproduce our results or to evaluate using the same metrics over your own test sets, please check out the [Evaluation README here](https://github.com/facebookresearch/seamless_communication/tree/main/src/seamless_communication/cli/m4t/evaluate).
152
+
153
+
154
+ ## Finetuning SeamlessM4T models
155
+ Please check out the [Finetuning README here](https://github.com/facebookresearch/seamless_communication/tree/main/src/seamless_communication/cli/m4t/finetune).
156
+
157
+ ## Transformers usage
158
+
159
+ SeamlessM4T is available in the 🤗 Transformers library, requiring minimal dependencies. Steps to get started:
160
+
161
+ 1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) from main and [sentencepiece](https://github.com/google/sentencepiece):
162
+
163
+ ```
164
+ pip install git+https://github.com/huggingface/transformers.git sentencepiece
165
+ ```
166
+
167
+ 2. Run the following Python code to generate speech samples. Here the target language is Russian:
168
+
169
+ ```py
170
+ from transformers import AutoProcessor, SeamlessM4Tv2Model
171
+ import torchaudio
172
+
173
+ processor = AutoProcessor.from_pretrained("facebook/seamless-m4t-v2-large")
174
+ model = SeamlessM4Tv2Model.from_pretrained("facebook/seamless-m4t-v2-large")
175
+
176
+ # from text
177
+ text_inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
178
+ audio_array_from_text = model.generate(**text_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
179
+
180
+ # from audio
181
+ audio, orig_freq = torchaudio.load("https://www2.cs.uic.edu/~i101/SoundFiles/preamble10.wav")
182
+ audio = torchaudio.functional.resample(audio, orig_freq=orig_freq, new_freq=16_000) # must be a 16 kHz waveform array
183
+ audio_inputs = processor(audios=audio, return_tensors="pt")
184
+ audio_array_from_audio = model.generate(**audio_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
185
+ ```
186
+
187
+ 3. Listen to the audio samples either in an ipynb notebook:
188
+
189
+ ```py
190
+ from IPython.display import Audio
191
+
192
+ sample_rate = model.sampling_rate
193
+ Audio(audio_array_from_text, rate=sample_rate)
194
+ # Audio(audio_array_from_audio, rate=sample_rate)
195
+ ```
196
+
197
+ Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
198
+
199
+ ```py
200
+ import scipy
201
+
202
+ sample_rate = model.sampling_rate
203
+ scipy.io.wavfile.write("out_from_text.wav", rate=sample_rate, data=audio_array_from_text)
204
+ # scipy.io.wavfile.write("out_from_audio.wav", rate=sample_rate, data=audio_array_from_audio)
205
+ ```
206
+ For more details on using the SeamlessM4T model for inference using the 🤗 Transformers library, refer to the
207
+ **[SeamlessM4T v2 docs](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t_v2)** or to this **hands-on [Google Colab](https://colab.research.google.com/github/ylacombe/scripts_and_notebooks/blob/main/v2_seamless_m4t_hugging_face.ipynb).**
208
+
209
+
210
+ ## Supported Languages:
211
+
212
+ Listed below, are the languages supported by SeamlessM4T-large (v1/v2).
213
+ The `source` column specifies whether a language is supported as source speech (`Sp`) and/or source text (`Tx`).
214
+ The `target` column specifies whether a language is supported as target speech (`Sp`) and/or target text (`Tx`).
215
+
216
+
217
+ | code | language | script | Source | Target |
218
+ | ---- | ---------------------- | ---------- | ------ | ------ |
219
+ | afr | Afrikaans | Latn | Sp, Tx | Tx |
220
+ | amh | Amharic | Ethi | Sp, Tx | Tx |
221
+ | arb | Modern Standard Arabic | Arab | Sp, Tx | Sp, Tx |
222
+ | ary | Moroccan Arabic | Arab | Sp, Tx | Tx |
223
+ | arz | Egyptian Arabic | Arab | Sp, Tx | Tx |
224
+ | asm | Assamese | Beng | Sp, Tx | Tx |
225
+ | ast | Asturian | Latn | Sp | \-- |
226
+ | azj | North Azerbaijani | Latn | Sp, Tx | Tx |
227
+ | bel | Belarusian | Cyrl | Sp, Tx | Tx |
228
+ | ben | Bengali | Beng | Sp, Tx | Sp, Tx |
229
+ | bos | Bosnian | Latn | Sp, Tx | Tx |
230
+ | bul | Bulgarian | Cyrl | Sp, Tx | Tx |
231
+ | cat | Catalan | Latn | Sp, Tx | Sp, Tx |
232
+ | ceb | Cebuano | Latn | Sp, Tx | Tx |
233
+ | ces | Czech | Latn | Sp, Tx | Sp, Tx |
234
+ | ckb | Central Kurdish | Arab | Sp, Tx | Tx |
235
+ | cmn | Mandarin Chinese | Hans | Sp, Tx | Sp, Tx |
236
+ | cmn_Hant | Mandarin Chinese | Hant | Sp, Tx | Sp, Tx |
237
+ | cym | Welsh | Latn | Sp, Tx | Sp, Tx |
238
+ | dan | Danish | Latn | Sp, Tx | Sp, Tx |
239
+ | deu | German | Latn | Sp, Tx | Sp, Tx |
240
+ | ell | Greek | Grek | Sp, Tx | Tx |
241
+ | eng | English | Latn | Sp, Tx | Sp, Tx |
242
+ | est | Estonian | Latn | Sp, Tx | Sp, Tx |
243
+ | eus | Basque | Latn | Sp, Tx | Tx |
244
+ | fin | Finnish | Latn | Sp, Tx | Sp, Tx |
245
+ | fra | French | Latn | Sp, Tx | Sp, Tx |
246
+ | fuv | Nigerian Fulfulde | Latn | Sp, Tx | Tx |
247
+ | gaz | West Central Oromo | Latn | Sp, Tx | Tx |
248
+ | gle | Irish | Latn | Sp, Tx | Tx |
249
+ | glg | Galician | Latn | Sp, Tx | Tx |
250
+ | guj | Gujarati | Gujr | Sp, Tx | Tx |
251
+ | heb | Hebrew | Hebr | Sp, Tx | Tx |
252
+ | hin | Hindi | Deva | Sp, Tx | Sp, Tx |
253
+ | hrv | Croatian | Latn | Sp, Tx | Tx |
254
+ | hun | Hungarian | Latn | Sp, Tx | Tx |
255
+ | hye | Armenian | Armn | Sp, Tx | Tx |
256
+ | ibo | Igbo | Latn | Sp, Tx | Tx |
257
+ | ind | Indonesian | Latn | Sp, Tx | Sp, Tx |
258
+ | isl | Icelandic | Latn | Sp, Tx | Tx |
259
+ | ita | Italian | Latn | Sp, Tx | Sp, Tx |
260
+ | jav | Javanese | Latn | Sp, Tx | Tx |
261
+ | jpn | Japanese | Jpan | Sp, Tx | Sp, Tx |
262
+ | kam | Kamba | Latn | Sp | \-- |
263
+ | kan | Kannada | Knda | Sp, Tx | Tx |
264
+ | kat | Georgian | Geor | Sp, Tx | Tx |
265
+ | kaz | Kazakh | Cyrl | Sp, Tx | Tx |
266
+ | kea | Kabuverdianu | Latn | Sp | \-- |
267
+ | khk | Halh Mongolian | Cyrl | Sp, Tx | Tx |
268
+ | khm | Khmer | Khmr | Sp, Tx | Tx |
269
+ | kir | Kyrgyz | Cyrl | Sp, Tx | Tx |
270
+ | kor | Korean | Kore | Sp, Tx | Sp, Tx |
271
+ | lao | Lao | Laoo | Sp, Tx | Tx |
272
+ | lit | Lithuanian | Latn | Sp, Tx | Tx |
273
+ | ltz | Luxembourgish | Latn | Sp | \-- |
274
+ | lug | Ganda | Latn | Sp, Tx | Tx |
275
+ | luo | Luo | Latn | Sp, Tx | Tx |
276
+ | lvs | Standard Latvian | Latn | Sp, Tx | Tx |
277
+ | mai | Maithili | Deva | Sp, Tx | Tx |
278
+ | mal | Malayalam | Mlym | Sp, Tx | Tx |
279
+ | mar | Marathi | Deva | Sp, Tx | Tx |
280
+ | mkd | Macedonian | Cyrl | Sp, Tx | Tx |
281
+ | mlt | Maltese | Latn | Sp, Tx | Sp, Tx |
282
+ | mni | Meitei | Beng | Sp, Tx | Tx |
283
+ | mya | Burmese | Mymr | Sp, Tx | Tx |
284
+ | nld | Dutch | Latn | Sp, Tx | Sp, Tx |
285
+ | nno | Norwegian Nynorsk | Latn | Sp, Tx | Tx |
286
+ | nob | Norwegian Bokmål | Latn | Sp, Tx | Tx |
287
+ | npi | Nepali | Deva | Sp, Tx | Tx |
288
+ | nya | Nyanja | Latn | Sp, Tx | Tx |
289
+ | oci | Occitan | Latn | Sp | \-- |
290
+ | ory | Odia | Orya | Sp, Tx | Tx |
291
+ | pan | Punjabi | Guru | Sp, Tx | Tx |
292
+ | pbt | Southern Pashto | Arab | Sp, Tx | Tx |
293
+ | pes | Western Persian | Arab | Sp, Tx | Sp, Tx |
294
+ | pol | Polish | Latn | Sp, Tx | Sp, Tx |
295
+ | por | Portuguese | Latn | Sp, Tx | Sp, Tx |
296
+ | ron | Romanian | Latn | Sp, Tx | Sp, Tx |
297
+ | rus | Russian | Cyrl | Sp, Tx | Sp, Tx |
298
+ | slk | Slovak | Latn | Sp, Tx | Sp, Tx |
299
+ | slv | Slovenian | Latn | Sp, Tx | Tx |
300
+ | sna | Shona | Latn | Sp, Tx | Tx |
301
+ | snd | Sindhi | Arab | Sp, Tx | Tx |
302
+ | som | Somali | Latn | Sp, Tx | Tx |
303
+ | spa | Spanish | Latn | Sp, Tx | Sp, Tx |
304
+ | srp | Serbian | Cyrl | Sp, Tx | Tx |
305
+ | swe | Swedish | Latn | Sp, Tx | Sp, Tx |
306
+ | swh | Swahili | Latn | Sp, Tx | Sp, Tx |
307
+ | tam | Tamil | Taml | Sp, Tx | Tx |
308
+ | tel | Telugu | Telu | Sp, Tx | Sp, Tx |
309
+ | tgk | Tajik | Cyrl | Sp, Tx | Tx |
310
+ | tgl | Tagalog | Latn | Sp, Tx | Sp, Tx |
311
+ | tha | Thai | Thai | Sp, Tx | Sp, Tx |
312
+ | tur | Turkish | Latn | Sp, Tx | Sp, Tx |
313
+ | ukr | Ukrainian | Cyrl | Sp, Tx | Sp, Tx |
314
+ | urd | Urdu | Arab | Sp, Tx | Sp, Tx |
315
+ | uzn | Northern Uzbek | Latn | Sp, Tx | Sp, Tx |
316
+ | vie | Vietnamese | Latn | Sp, Tx | Sp, Tx |
317
+ | xho | Xhosa | Latn | Sp | \-- |
318
+ | yor | Yoruba | Latn | Sp, Tx | Tx |
319
+ | yue | Cantonese | Hant | Sp, Tx | Tx |
320
+ | zlm | Colloquial Malay | Latn | Sp | \-- |
321
+ | zsm | Standard Malay | Latn | Tx | Tx |
322
+ | zul | Zulu | Latn | Sp, Tx | Tx |
323
+
324
+
325
+ Note that seamlessM4T-medium supports 200 languages in the text modality, and is based on NLLB-200 (see full list in [asset card](https://github.com/facebookresearch/seamless_communication/blob/main/src/seamless_communication/cards/unity_nllb-200.yaml))
326
+
327
+ ## Citation
328
+ For SeamlessM4T v2, please cite :
329
+ ```bibtex
330
+ @inproceedings{seamless2023,
331
+ title="Seamless: Multilingual Expressive and Streaming Speech Translation",
332
+ author="{Seamless Communication}, Lo{\"i}c Barrault, Yu-An Chung, Mariano Coria Meglioli, David Dale, Ning Dong, Mark Duppenthaler, Paul-Ambroise Duquenne, Brian Ellis, Hady Elsahar, Justin Haaheim, John Hoffman, Min-Jae Hwang, Hirofumi Inaguma, Christopher Klaiber, Ilia Kulikov, Pengwei Li, Daniel Licht, Jean Maillard, Ruslan Mavlyutov, Alice Rakotoarison, Kaushik Ram Sadagopan, Abinesh Ramakrishnan, Tuan Tran, Guillaume Wenzek, Yilin Yang, Ethan Ye, Ivan Evtimov, Pierre Fernandez, Cynthia Gao, Prangthip Hansanti, Elahe Kalbassi, Amanda Kallet, Artyom Kozhevnikov, Gabriel Mejia, Robin San Roman, Christophe Touret, Corinne Wong, Carleigh Wood, Bokai Yu, Pierre Andrews, Can Balioglu, Peng-Jen Chen, Marta R. Costa-juss{\`a}, Maha Elbayad, Hongyu Gong, Francisco Guzm{\'a}n, Kevin Heffernan, Somya Jain, Justine Kao, Ann Lee, Xutai Ma, Alex Mourachko, Benjamin Peloquin, Juan Pino, Sravya Popuri, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Anna Sun, Paden Tomasello, Changhan Wang, Jeff Wang, Skyler Wang, Mary Williamson",
333
+ journal={ArXiv},
334
+ year={2023}
335
+ }
336
+ ```
added_tokens.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__afr__": 256001,
3
+ "__amh__": 256002,
4
+ "__arb__": 256003,
5
+ "__ary__": 256004,
6
+ "__arz__": 256005,
7
+ "__asm__": 256006,
8
+ "__azj__": 256007,
9
+ "__bel__": 256008,
10
+ "__ben__": 256009,
11
+ "__bos__": 256010,
12
+ "__bul__": 256011,
13
+ "__cat__": 256012,
14
+ "__ceb__": 256013,
15
+ "__ces__": 256014,
16
+ "__ckb__": 256015,
17
+ "__cmn_Hant__": 256017,
18
+ "__cmn__": 256016,
19
+ "__cym__": 256018,
20
+ "__dan__": 256019,
21
+ "__deu__": 256020,
22
+ "__ell__": 256021,
23
+ "__eng__": 256022,
24
+ "__est__": 256023,
25
+ "__eus__": 256024,
26
+ "__fin__": 256025,
27
+ "__fra__": 256026,
28
+ "__fuv__": 256027,
29
+ "__gaz__": 256028,
30
+ "__gle__": 256029,
31
+ "__glg__": 256030,
32
+ "__guj__": 256031,
33
+ "__heb__": 256032,
34
+ "__hin__": 256033,
35
+ "__hrv__": 256034,
36
+ "__hun__": 256035,
37
+ "__hye__": 256036,
38
+ "__ibo__": 256037,
39
+ "__ind__": 256038,
40
+ "__isl__": 256039,
41
+ "__ita__": 256040,
42
+ "__jav__": 256041,
43
+ "__jpn__": 256042,
44
+ "__kan__": 256043,
45
+ "__kat__": 256044,
46
+ "__kaz__": 256045,
47
+ "__khk__": 256046,
48
+ "__khm__": 256047,
49
+ "__kir__": 256048,
50
+ "__kor__": 256049,
51
+ "__lao__": 256050,
52
+ "__lit__": 256051,
53
+ "__lug__": 256052,
54
+ "__luo__": 256053,
55
+ "__lvs__": 256054,
56
+ "__mai__": 256055,
57
+ "__mal__": 256056,
58
+ "__mar__": 256057,
59
+ "__mkd__": 256058,
60
+ "__mlt__": 256059,
61
+ "__mni__": 256060,
62
+ "__mya__": 256061,
63
+ "__nld__": 256062,
64
+ "__nno__": 256063,
65
+ "__nob__": 256064,
66
+ "__npi__": 256065,
67
+ "__nya__": 256066,
68
+ "__ory__": 256067,
69
+ "__pan__": 256068,
70
+ "__pbt__": 256069,
71
+ "__pes__": 256070,
72
+ "__pol__": 256071,
73
+ "__por__": 256072,
74
+ "__ron__": 256073,
75
+ "__rus__": 256074,
76
+ "__sat__": 256075,
77
+ "__slk__": 256076,
78
+ "__slv__": 256077,
79
+ "__sna__": 256078,
80
+ "__snd__": 256079,
81
+ "__som__": 256080,
82
+ "__spa__": 256081,
83
+ "__srp__": 256082,
84
+ "__swe__": 256083,
85
+ "__swh__": 256084,
86
+ "__tam__": 256085,
87
+ "__tel__": 256086,
88
+ "__tgk__": 256087,
89
+ "__tgl__": 256088,
90
+ "__tha__": 256089,
91
+ "__tur__": 256090,
92
+ "__ukr__": 256091,
93
+ "__urd__": 256092,
94
+ "__uzn__": 256093,
95
+ "__vie__": 256094,
96
+ "__yor__": 256095,
97
+ "__yue__": 256096,
98
+ "__zlm__": 256097,
99
+ "__zul__": 256098
100
+ }
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "adaptor_dropout": 0.1,
5
+ "adaptor_kernel_size": 8,
6
+ "adaptor_stride": 8,
7
+ "add_adapter": true,
8
+ "architectures": [
9
+ "SeamlessM4Tv2Model"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 2,
13
+ "char_vocab_size": 10943,
14
+ "conv_depthwise_kernel_size": 31,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 8192,
17
+ "decoder_layerdrop": 0.05,
18
+ "decoder_layers": 24,
19
+ "decoder_start_token_id": 3,
20
+ "dropout": 0.1,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 8192,
23
+ "encoder_layerdrop": 0.05,
24
+ "encoder_layers": 24,
25
+ "eos_token_id": 3,
26
+ "feature_projection_input_dim": 160,
27
+ "hidden_size": 1024,
28
+ "initializer_range": 0.02,
29
+ "is_encoder_decoder": true,
30
+ "lang_embed_dim": 256,
31
+ "layer_norm_eps": 1e-05,
32
+ "leaky_relu_slope": 0.1,
33
+ "left_max_position_embeddings": 64,
34
+ "max_new_tokens": 256,
35
+ "max_position_embeddings": 4096,
36
+ "model_type": "seamless_m4t_v2",
37
+ "num_adapter_layers": 1,
38
+ "num_attention_heads": 16,
39
+ "num_hidden_layers": 24,
40
+ "pad_token_id": 0,
41
+ "position_embeddings_type": "relative_key",
42
+ "resblock_dilation_sizes": [
43
+ [
44
+ 1,
45
+ 3,
46
+ 5
47
+ ],
48
+ [
49
+ 1,
50
+ 3,
51
+ 5
52
+ ],
53
+ [
54
+ 1,
55
+ 3,
56
+ 5
57
+ ]
58
+ ],
59
+ "resblock_kernel_sizes": [
60
+ 3,
61
+ 7,
62
+ 11
63
+ ],
64
+ "right_max_position_embeddings": 8,
65
+ "sampling_rate": 16000,
66
+ "scale_embedding": true,
67
+ "speech_encoder_attention_heads": 16,
68
+ "speech_encoder_chunk_size": 20000,
69
+ "speech_encoder_dropout": 0.0,
70
+ "speech_encoder_hidden_act": "swish",
71
+ "speech_encoder_intermediate_size": 4096,
72
+ "speech_encoder_layerdrop": 0.1,
73
+ "speech_encoder_layers": 24,
74
+ "speech_encoder_left_chunk_num": 128,
75
+ "spkr_embed_dim": 256,
76
+ "t2u_bos_token_id": 0,
77
+ "t2u_decoder_attention_heads": 16,
78
+ "t2u_decoder_ffn_dim": 8192,
79
+ "t2u_decoder_layers": 6,
80
+ "t2u_encoder_attention_heads": 16,
81
+ "t2u_encoder_ffn_dim": 8192,
82
+ "t2u_encoder_layers": 6,
83
+ "t2u_eos_token_id": 2,
84
+ "t2u_max_position_embeddings": 4096,
85
+ "t2u_pad_token_id": 1,
86
+ "t2u_variance_pred_dropout": 0.5,
87
+ "t2u_variance_predictor_embed_dim": 1024,
88
+ "t2u_variance_predictor_hidden_dim": 256,
89
+ "t2u_variance_predictor_kernel_size": 3,
90
+ "t2u_vocab_size": 10082,
91
+ "torch_dtype": "float32",
92
+ "transformers_version": "4.36.0.dev0",
93
+ "unit_embed_dim": 1280,
94
+ "unit_hifi_gan_vocab_size": 10000,
95
+ "upsample_initial_channel": 512,
96
+ "upsample_kernel_sizes": [
97
+ 11,
98
+ 8,
99
+ 8,
100
+ 4,
101
+ 4
102
+ ],
103
+ "upsample_rates": [
104
+ 5,
105
+ 4,
106
+ 4,
107
+ 2,
108
+ 2
109
+ ],
110
+ "use_cache": true,
111
+ "var_pred_dropout": 0.5,
112
+ "variance_predictor_kernel_size": 3,
113
+ "vocab_size": 256102,
114
+ "vocoder_num_langs": 36,
115
+ "vocoder_num_spkrs": 200,
116
+ "vocoder_offset": 4
117
+ }
generation_config.json ADDED
The diff for this file is too large to render. See raw diff
 
m4t_v2_multitask_unity2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ebd8fe5fbf99dc2363f7da7fa6e318cf9317f682cfc0a252ade38e0a3fbacab
3
+ size 11386771266
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85cab984fbc111f8713827c440499453b9e66f262862866eeed8725c302ba2ac
3
+ size 4999163080
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9536dc05892a6ca8410bcfea763dde422e2430c3cc1f3acd26c55182c8989017
3
+ size 4238114628
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "language_code": [
5
+ "__afr__",
6
+ "__amh__",
7
+ "__arb__",
8
+ "__ary__",
9
+ "__arz__",
10
+ "__asm__",
11
+ "__azj__",
12
+ "__bel__",
13
+ "__ben__",
14
+ "__bos__",
15
+ "__bul__",
16
+ "__cat__",
17
+ "__ceb__",
18
+ "__ces__",
19
+ "__ckb__",
20
+ "__cmn__",
21
+ "__cmn_Hant__",
22
+ "__cym__",
23
+ "__dan__",
24
+ "__deu__",
25
+ "__ell__",
26
+ "__eng__",
27
+ "__est__",
28
+ "__eus__",
29
+ "__fin__",
30
+ "__fra__",
31
+ "__fuv__",
32
+ "__gaz__",
33
+ "__gle__",
34
+ "__glg__",
35
+ "__guj__",
36
+ "__heb__",
37
+ "__hin__",
38
+ "__hrv__",
39
+ "__hun__",
40
+ "__hye__",
41
+ "__ibo__",
42
+ "__ind__",
43
+ "__isl__",
44
+ "__ita__",
45
+ "__jav__",
46
+ "__jpn__",
47
+ "__kan__",
48
+ "__kat__",
49
+ "__kaz__",
50
+ "__khk__",
51
+ "__khm__",
52
+ "__kir__",
53
+ "__kor__",
54
+ "__lao__",
55
+ "__lit__",
56
+ "__lug__",
57
+ "__luo__",
58
+ "__lvs__",
59
+ "__mai__",
60
+ "__mal__",
61
+ "__mar__",
62
+ "__mkd__",
63
+ "__mlt__",
64
+ "__mni__",
65
+ "__mya__",
66
+ "__nld__",
67
+ "__nno__",
68
+ "__nob__",
69
+ "__npi__",
70
+ "__nya__",
71
+ "__ory__",
72
+ "__pan__",
73
+ "__pbt__",
74
+ "__pes__",
75
+ "__pol__",
76
+ "__por__",
77
+ "__ron__",
78
+ "__rus__",
79
+ "__sat__",
80
+ "__slk__",
81
+ "__slv__",
82
+ "__sna__",
83
+ "__snd__",
84
+ "__som__",
85
+ "__spa__",
86
+ "__srp__",
87
+ "__swe__",
88
+ "__swh__",
89
+ "__tam__",
90
+ "__tel__",
91
+ "__tgk__",
92
+ "__tgl__",
93
+ "__tha__",
94
+ "__tur__",
95
+ "__ukr__",
96
+ "__urd__",
97
+ "__uzn__",
98
+ "__vie__",
99
+ "__yor__",
100
+ "__yue__",
101
+ "__zlm__",
102
+ "__zul__"
103
+ ],
104
+ "num_mel_bins": 80,
105
+ "padding_side": "right",
106
+ "padding_value": 0.0,
107
+ "processor_class": "SeamlessM4TProcessor",
108
+ "return_attention_mask": true,
109
+ "sampling_rate": 16000,
110
+ "stride": 2
111
+ }
seamlessM4T_v2_large.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2122cedcffc532d6048847092414e638cfb4db402881cb8146a606008e9ff56
3
+ size 9070060243
seamlessm4t_arch.svg ADDED
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026a76827537db9f1348e4d5aaa127bb10a2f2ff633243f3a52d16be82d73f9d
3
+ size 5165809
special_tokens_map.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__afr__",
4
+ "__amh__",
5
+ "__arb__",
6
+ "__ary__",
7
+ "__arz__",
8
+ "__asm__",
9
+ "__azj__",
10
+ "__bel__",
11
+ "__ben__",
12
+ "__bos__",
13
+ "__bul__",
14
+ "__cat__",
15
+ "__ceb__",
16
+ "__ces__",
17
+ "__ckb__",
18
+ "__cmn__",
19
+ "__cmn_Hant__",
20
+ "__cym__",
21
+ "__dan__",
22
+ "__deu__",
23
+ "__ell__",
24
+ "__eng__",
25
+ "__est__",
26
+ "__eus__",
27
+ "__fin__",
28
+ "__fra__",
29
+ "__fuv__",
30
+ "__gaz__",
31
+ "__gle__",
32
+ "__glg__",
33
+ "__guj__",
34
+ "__heb__",
35
+ "__hin__",
36
+ "__hrv__",
37
+ "__hun__",
38
+ "__hye__",
39
+ "__ibo__",
40
+ "__ind__",
41
+ "__isl__",
42
+ "__ita__",
43
+ "__jav__",
44
+ "__jpn__",
45
+ "__kan__",
46
+ "__kat__",
47
+ "__kaz__",
48
+ "__khk__",
49
+ "__khm__",
50
+ "__kir__",
51
+ "__kor__",
52
+ "__lao__",
53
+ "__lit__",
54
+ "__lug__",
55
+ "__luo__",
56
+ "__lvs__",
57
+ "__mai__",
58
+ "__mal__",
59
+ "__mar__",
60
+ "__mkd__",
61
+ "__mlt__",
62
+ "__mni__",
63
+ "__mya__",
64
+ "__nld__",
65
+ "__nno__",
66
+ "__nob__",
67
+ "__npi__",
68
+ "__nya__",
69
+ "__ory__",
70
+ "__pan__",
71
+ "__pbt__",
72
+ "__pes__",
73
+ "__pol__",
74
+ "__por__",
75
+ "__ron__",
76
+ "__rus__",
77
+ "__sat__",
78
+ "__slk__",
79
+ "__slv__",
80
+ "__sna__",
81
+ "__snd__",
82
+ "__som__",
83
+ "__spa__",
84
+ "__srp__",
85
+ "__swe__",
86
+ "__swh__",
87
+ "__tam__",
88
+ "__tel__",
89
+ "__tgk__",
90
+ "__tgl__",
91
+ "__tha__",
92
+ "__tur__",
93
+ "__ukr__",
94
+ "__urd__",
95
+ "__uzn__",
96
+ "__vie__",
97
+ "__yor__",
98
+ "__yue__",
99
+ "__zlm__",
100
+ "__zul__"
101
+ ],
102
+ "bos_token": {
103
+ "content": "<s>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false
108
+ },
109
+ "cls_token": {
110
+ "content": "<s>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false
115
+ },
116
+ "eos_token": {
117
+ "content": "</s>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false
122
+ },
123
+ "pad_token": {
124
+ "content": "<pad>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false
129
+ },
130
+ "sep_token": {
131
+ "content": "</s>",
132
+ "lstrip": false,
133
+ "normalized": false,
134
+ "rstrip": false,
135
+ "single_word": false
136
+ },
137
+ "unk_token": {
138
+ "content": "<unk>",
139
+ "lstrip": false,
140
+ "normalized": false,
141
+ "rstrip": false,
142
+ "single_word": false
143
+ }
144
+ }
spm_char_lang38_tc.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e7f2075dbc38dbe11d2414bfa4fb8e900022e87bbff4f74c97817e32a7ab493
3
+ size 368901
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026a76827537db9f1348e4d5aaa127bb10a2f2ff633243f3a52d16be82d73f9d
3
+ size 5165809
tokenizer_config.json ADDED
@@ -0,0 +1,933 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "256001": {
36
+ "content": "__afr__",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "256002": {
44
+ "content": "__amh__",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "256003": {
52
+ "content": "__arb__",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "256004": {
60
+ "content": "__ary__",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "256005": {
68
+ "content": "__arz__",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "256006": {
76
+ "content": "__asm__",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "256007": {
84
+ "content": "__azj__",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "256008": {
92
+ "content": "__bel__",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "256009": {
100
+ "content": "__ben__",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "256010": {
108
+ "content": "__bos__",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "256011": {
116
+ "content": "__bul__",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "256012": {
124
+ "content": "__cat__",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "256013": {
132
+ "content": "__ceb__",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "256014": {
140
+ "content": "__ces__",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "256015": {
148
+ "content": "__ckb__",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "256016": {
156
+ "content": "__cmn__",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "256017": {
164
+ "content": "__cmn_Hant__",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "256018": {
172
+ "content": "__cym__",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "256019": {
180
+ "content": "__dan__",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "256020": {
188
+ "content": "__deu__",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "256021": {
196
+ "content": "__ell__",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "256022": {
204
+ "content": "__eng__",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "256023": {
212
+ "content": "__est__",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "256024": {
220
+ "content": "__eus__",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "256025": {
228
+ "content": "__fin__",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "256026": {
236
+ "content": "__fra__",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "256027": {
244
+ "content": "__fuv__",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "256028": {
252
+ "content": "__gaz__",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "256029": {
260
+ "content": "__gle__",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "256030": {
268
+ "content": "__glg__",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "256031": {
276
+ "content": "__guj__",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "256032": {
284
+ "content": "__heb__",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "256033": {
292
+ "content": "__hin__",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "256034": {
300
+ "content": "__hrv__",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "256035": {
308
+ "content": "__hun__",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "256036": {
316
+ "content": "__hye__",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "256037": {
324
+ "content": "__ibo__",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "256038": {
332
+ "content": "__ind__",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "256039": {
340
+ "content": "__isl__",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "256040": {
348
+ "content": "__ita__",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "256041": {
356
+ "content": "__jav__",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "256042": {
364
+ "content": "__jpn__",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "256043": {
372
+ "content": "__kan__",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "256044": {
380
+ "content": "__kat__",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "256045": {
388
+ "content": "__kaz__",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "256046": {
396
+ "content": "__khk__",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "256047": {
404
+ "content": "__khm__",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "256048": {
412
+ "content": "__kir__",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "256049": {
420
+ "content": "__kor__",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "256050": {
428
+ "content": "__lao__",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "256051": {
436
+ "content": "__lit__",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "256052": {
444
+ "content": "__lug__",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "256053": {
452
+ "content": "__luo__",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "256054": {
460
+ "content": "__lvs__",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "256055": {
468
+ "content": "__mai__",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "256056": {
476
+ "content": "__mal__",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "256057": {
484
+ "content": "__mar__",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "256058": {
492
+ "content": "__mkd__",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "256059": {
500
+ "content": "__mlt__",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "256060": {
508
+ "content": "__mni__",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "256061": {
516
+ "content": "__mya__",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "256062": {
524
+ "content": "__nld__",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "256063": {
532
+ "content": "__nno__",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "256064": {
540
+ "content": "__nob__",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "256065": {
548
+ "content": "__npi__",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "256066": {
556
+ "content": "__nya__",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "256067": {
564
+ "content": "__ory__",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "256068": {
572
+ "content": "__pan__",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "256069": {
580
+ "content": "__pbt__",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "256070": {
588
+ "content": "__pes__",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "256071": {
596
+ "content": "__pol__",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "256072": {
604
+ "content": "__por__",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "256073": {
612
+ "content": "__ron__",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "256074": {
620
+ "content": "__rus__",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "256075": {
628
+ "content": "__sat__",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "256076": {
636
+ "content": "__slk__",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "256077": {
644
+ "content": "__slv__",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "256078": {
652
+ "content": "__sna__",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "256079": {
660
+ "content": "__snd__",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "256080": {
668
+ "content": "__som__",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "256081": {
676
+ "content": "__spa__",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "256082": {
684
+ "content": "__srp__",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "256083": {
692
+ "content": "__swe__",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "256084": {
700
+ "content": "__swh__",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "256085": {
708
+ "content": "__tam__",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "256086": {
716
+ "content": "__tel__",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "256087": {
724
+ "content": "__tgk__",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "256088": {
732
+ "content": "__tgl__",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "256089": {
740
+ "content": "__tha__",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "256090": {
748
+ "content": "__tur__",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "256091": {
756
+ "content": "__ukr__",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "256092": {
764
+ "content": "__urd__",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "256093": {
772
+ "content": "__uzn__",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "256094": {
780
+ "content": "__vie__",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "256095": {
788
+ "content": "__yor__",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "256096": {
796
+ "content": "__yue__",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "256097": {
804
+ "content": "__zlm__",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "256098": {
812
+ "content": "__zul__",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ }
819
+ },
820
+ "additional_special_tokens": [
821
+ "__afr__",
822
+ "__amh__",
823
+ "__arb__",
824
+ "__ary__",
825
+ "__arz__",
826
+ "__asm__",
827
+ "__azj__",
828
+ "__bel__",
829
+ "__ben__",
830
+ "__bos__",
831
+ "__bul__",
832
+ "__cat__",
833
+ "__ceb__",
834
+ "__ces__",
835
+ "__ckb__",
836
+ "__cmn__",
837
+ "__cmn_Hant__",
838
+ "__cym__",
839
+ "__dan__",
840
+ "__deu__",
841
+ "__ell__",
842
+ "__eng__",
843
+ "__est__",
844
+ "__eus__",
845
+ "__fin__",
846
+ "__fra__",
847
+ "__fuv__",
848
+ "__gaz__",
849
+ "__gle__",
850
+ "__glg__",
851
+ "__guj__",
852
+ "__heb__",
853
+ "__hin__",
854
+ "__hrv__",
855
+ "__hun__",
856
+ "__hye__",
857
+ "__ibo__",
858
+ "__ind__",
859
+ "__isl__",
860
+ "__ita__",
861
+ "__jav__",
862
+ "__jpn__",
863
+ "__kan__",
864
+ "__kat__",
865
+ "__kaz__",
866
+ "__khk__",
867
+ "__khm__",
868
+ "__kir__",
869
+ "__kor__",
870
+ "__lao__",
871
+ "__lit__",
872
+ "__lug__",
873
+ "__luo__",
874
+ "__lvs__",
875
+ "__mai__",
876
+ "__mal__",
877
+ "__mar__",
878
+ "__mkd__",
879
+ "__mlt__",
880
+ "__mni__",
881
+ "__mya__",
882
+ "__nld__",
883
+ "__nno__",
884
+ "__nob__",
885
+ "__npi__",
886
+ "__nya__",
887
+ "__ory__",
888
+ "__pan__",
889
+ "__pbt__",
890
+ "__pes__",
891
+ "__pol__",
892
+ "__por__",
893
+ "__ron__",
894
+ "__rus__",
895
+ "__sat__",
896
+ "__slk__",
897
+ "__slv__",
898
+ "__sna__",
899
+ "__snd__",
900
+ "__som__",
901
+ "__spa__",
902
+ "__srp__",
903
+ "__swe__",
904
+ "__swh__",
905
+ "__tam__",
906
+ "__tel__",
907
+ "__tgk__",
908
+ "__tgl__",
909
+ "__tha__",
910
+ "__tur__",
911
+ "__ukr__",
912
+ "__urd__",
913
+ "__uzn__",
914
+ "__vie__",
915
+ "__yor__",
916
+ "__yue__",
917
+ "__zlm__",
918
+ "__zul__"
919
+ ],
920
+ "bos_token": "<s>",
921
+ "clean_up_tokenization_spaces": true,
922
+ "cls_token": "<s>",
923
+ "eos_token": "</s>",
924
+ "model_max_length": 1000000000000000019884624838656,
925
+ "pad_token": "<pad>",
926
+ "processor_class": "SeamlessM4TProcessor",
927
+ "sep_token": "</s>",
928
+ "sp_model_kwargs": {},
929
+ "src_lang": "__eng__",
930
+ "tgt_lang": "__fra__",
931
+ "tokenizer_class": "SeamlessM4TTokenizer",
932
+ "unk_token": "<unk>"
933
+ }
vocoder_v2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c50c3edd3fb08704c10542bf3ec72e8a96aaba4ec09fb6ac1fa64172c8ca13
3
+ size 167785015