Hugging Face's logo

balaramas
/
seamless-m4t-large-t2t-en-hi

Text-to-Speech
Transformers
PyTorch
seamless_m4t
feature-extraction
SeamlessM4T
Model card Files Community
balaramas commited on
Commit
0bfb466
•
1 Parent(s): 946fede

Upload 9 files

Browse files
Files changed (8) hide show
  1. README.md +129 -0
  2. added_tokens.json +104 -0
  3. config.json +114 -0
  4. generation_config.json +186 -0
  5. preprocessor_config.json +111 -0
  6. sentencepiece.bpe.model +3 -0
  7. special_tokens_map.json +112 -0
  8. tokenizer_config.json +938 -0
README.md ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ tags:
4
+ - SeamlessM4T
5
+ - seamless_m4t
6
+ license: cc-by-nc-4.0
7
+ library_name: transformers
8
+ pipeline_tag: text-to-speech
9
+ ---
10
+
11
+ # SeamlessM4T Large
12
+
13
+ SeamlessM4T is a collection of models designed to provide high quality translation, allowing people from different
14
+ linguistic communities to communicate effortlessly through speech and text.
15
+
16
+ This repository hosts 🤗 Hugging Face's [implementation](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t) of SeamlessM4T.
17
+
18
+ -------------------
19
+
20
+ **🌟 SeamlessM4T v2, an improved version of this version with a novel architecture, has been released [here](https://huggingface.co/facebook/seamless-m4t-v2-large).
21
+ This new model improves over SeamlessM4T v1 in quality as well as inference speed in speech generation tasks.**
22
+
23
+ **SeamlessM4T v2 is also supported by 🤗 Transformers, more on it [in the model card of this new version](https://huggingface.co/facebook/seamless-m4t-v2-large#transformers-usage) or directly in [🤗 Transformers docs](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t_v2).**
24
+
25
+ -------------------
26
+
27
+ SeamlessM4T Large covers:
28
+ - 📥 101 languages for speech input
29
+ - ⌨️ [96 Languages](https://huggingface.co/ylacombe/hf-seamless-m4t-large/blob/main/generation_config.json#L48-L145) for text input/output
30
+ - 🗣️ [35 languages](https://huggingface.co/ylacombe/hf-seamless-m4t-large/blob/main/generation_config.json#L149-L184) for speech output.
31
+
32
+ This is the "large" variant of the unified model, which enables multiple tasks without relying on multiple separate models:
33
+ - Speech-to-speech translation (S2ST)
34
+ - Speech-to-text translation (S2TT)
35
+ - Text-to-speech translation (T2ST)
36
+ - Text-to-text translation (T2TT)
37
+ - Automatic speech recognition (ASR)
38
+
39
+ You can perform all the above tasks from one single model, [`SeamlessM4TModel`](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel), but each task also has its own dedicated sub-model.
40
+
41
+
42
+ ## 🤗 Usage
43
+
44
+ First, load the processor and a checkpoint of the model:
45
+
46
+ ```python
47
+ >>> from transformers import AutoProcessor, SeamlessM4TModel
48
+
49
+ >>> processor = AutoProcessor.from_pretrained("facebook/hf-seamless-m4t-large")
50
+ >>> model = SeamlessM4TModel.from_pretrained("facebook/hf-seamless-m4t-large")
51
+ ```
52
+
53
+ You can seamlessly use this model on text or on audio, to generated either translated text or translated audio.
54
+
55
+ Here is how to use the processor to process text and audio:
56
+
57
+ ```python
58
+ >>> # let's load an audio sample from an Arabic speech corpus
59
+ >>> from datasets import load_dataset
60
+ >>> dataset = load_dataset("arabic_speech_corpus", split="test", streaming=True)
61
+ >>> audio_sample = next(iter(dataset))["audio"]
62
+
63
+ >>> # now, process it
64
+ >>> audio_inputs = processor(audios=audio_sample["array"], return_tensors="pt")
65
+
66
+ >>> # now, process some English test as well
67
+ >>> text_inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
68
+ ```
69
+
70
+
71
+ ### Speech
72
+
73
+ [`SeamlessM4TModel`](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel) can *seamlessly* generate text or speech with few or no changes. Let's target Russian voice translation:
74
+
75
+ ```python
76
+ >>> audio_array_from_text = model.generate(**text_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
77
+ >>> audio_array_from_audio = model.generate(**audio_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
78
+ ```
79
+
80
+ With basically the same code, I've translated English text and Arabic speech to Russian speech samples.
81
+
82
+ ### Text
83
+
84
+ Similarly, you can generate translated text from audio files or from text with the same model. You only have to pass `generate_speech=False` to [`SeamlessM4TModel.generate`](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel.generate).
85
+ This time, let's translate to French.
86
+
87
+ ```python
88
+ >>> # from audio
89
+ >>> output_tokens = model.generate(**audio_inputs, tgt_lang="fra", generate_speech=False)
90
+ >>> translated_text_from_audio = processor.decode(output_tokens[0].tolist(), skip_special_tokens=True)
91
+
92
+ >>> # from text
93
+ >>> output_tokens = model.generate(**text_inputs, tgt_lang="fra", generate_speech=False)
94
+ >>> translated_text_from_text = processor.decode(output_tokens[0].tolist(), skip_special_tokens=True)
95
+ ```
96
+
97
+ ### Tips
98
+
99
+
100
+ #### 1. Use dedicated models
101
+
102
+ [`SeamlessM4TModel`](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel) is transformers top level model to generate speech and text, but you can also use dedicated models that perform the task without additional components, thus reducing the memory footprint.
103
+ For example, you can replace the audio-to-audio generation snippet with the model dedicated to the S2ST task, the rest is exactly the same code:
104
+
105
+ ```python
106
+ >>> from transformers import SeamlessM4TForSpeechToSpeech
107
+ >>> model = SeamlessM4TForSpeechToSpeech.from_pretrained("facebook/hf-seamless-m4t-large")
108
+ ```
109
+
110
+ Or you can replace the text-to-text generation snippet with the model dedicated to the T2TT task, you only have to remove `generate_speech=False`.
111
+
112
+ ```python
113
+ >>> from transformers import SeamlessM4TForTextToText
114
+ >>> model = SeamlessM4TForTextToText.from_pretrained("facebook/hf-seamless-m4t-large")
115
+ ```
116
+
117
+ Feel free to try out [`SeamlessM4TForSpeechToText`](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t#transformers.SeamlessM4TForSpeechToText) and [`SeamlessM4TForTextToSpeech`](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t#transformers.SeamlessM4TForTextToSpeech) as well.
118
+
119
+ #### 2. Change the speaker identity
120
+
121
+ You have the possibility to change the speaker used for speech synthesis with the `spkr_id` argument. Some `spkr_id` works better than other for some languages!
122
+
123
+ #### 3. Change the generation strategy
124
+
125
+ You can use different [generation strategies](https://huggingface.co/docs/transformers/v4.34.1/en/generation_strategies#text-generation-strategies) for speech and text generation, e.g `.generate(input_ids=input_ids, text_num_beams=4, speech_do_sample=True)` which will successively perform beam-search decoding on the text model, and multinomial sampling on the speech model.
126
+
127
+ #### 4. Generate speech and text at the same time
128
+
129
+ Use `return_intermediate_token_ids=True` with [`SeamlessM4TModel`](https://huggingface.co/docs/transformers/main/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel) to return both speech and text !
added_tokens.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 3,
3
+ "<pad>": 0,
4
+ "<s>": 2,
5
+ "<unk>": 1,
6
+ "__afr__": 256001,
7
+ "__amh__": 256002,
8
+ "__arb__": 256003,
9
+ "__ary__": 256004,
10
+ "__arz__": 256005,
11
+ "__asm__": 256006,
12
+ "__azj__": 256007,
13
+ "__bel__": 256008,
14
+ "__ben__": 256009,
15
+ "__bos__": 256010,
16
+ "__bul__": 256011,
17
+ "__cat__": 256012,
18
+ "__ceb__": 256013,
19
+ "__ces__": 256014,
20
+ "__ckb__": 256015,
21
+ "__cmn_Hant__": 256017,
22
+ "__cmn__": 256016,
23
+ "__cym__": 256018,
24
+ "__dan__": 256019,
25
+ "__deu__": 256020,
26
+ "__ell__": 256021,
27
+ "__eng__": 256022,
28
+ "__est__": 256023,
29
+ "__eus__": 256024,
30
+ "__fin__": 256025,
31
+ "__fra__": 256026,
32
+ "__fuv__": 256027,
33
+ "__gaz__": 256028,
34
+ "__gle__": 256029,
35
+ "__glg__": 256030,
36
+ "__guj__": 256031,
37
+ "__heb__": 256032,
38
+ "__hin__": 256033,
39
+ "__hrv__": 256034,
40
+ "__hun__": 256035,
41
+ "__hye__": 256036,
42
+ "__ibo__": 256037,
43
+ "__ind__": 256038,
44
+ "__isl__": 256039,
45
+ "__ita__": 256040,
46
+ "__jav__": 256041,
47
+ "__jpn__": 256042,
48
+ "__kan__": 256043,
49
+ "__kat__": 256044,
50
+ "__kaz__": 256045,
51
+ "__khk__": 256046,
52
+ "__khm__": 256047,
53
+ "__kir__": 256048,
54
+ "__kor__": 256049,
55
+ "__lao__": 256050,
56
+ "__lit__": 256051,
57
+ "__lug__": 256052,
58
+ "__luo__": 256053,
59
+ "__lvs__": 256054,
60
+ "__mai__": 256055,
61
+ "__mal__": 256056,
62
+ "__mar__": 256057,
63
+ "__mkd__": 256058,
64
+ "__mlt__": 256059,
65
+ "__mni__": 256060,
66
+ "__mya__": 256061,
67
+ "__nld__": 256062,
68
+ "__nno__": 256063,
69
+ "__nob__": 256064,
70
+ "__npi__": 256065,
71
+ "__nya__": 256066,
72
+ "__ory__": 256067,
73
+ "__pan__": 256068,
74
+ "__pbt__": 256069,
75
+ "__pes__": 256070,
76
+ "__pol__": 256071,
77
+ "__por__": 256072,
78
+ "__ron__": 256073,
79
+ "__rus__": 256074,
80
+ "__sat__": 256075,
81
+ "__slk__": 256076,
82
+ "__slv__": 256077,
83
+ "__sna__": 256078,
84
+ "__snd__": 256079,
85
+ "__som__": 256080,
86
+ "__spa__": 256081,
87
+ "__srp__": 256082,
88
+ "__swe__": 256083,
89
+ "__swh__": 256084,
90
+ "__tam__": 256085,
91
+ "__tel__": 256086,
92
+ "__tgk__": 256087,
93
+ "__tgl__": 256088,
94
+ "__tha__": 256089,
95
+ "__tur__": 256090,
96
+ "__ukr__": 256091,
97
+ "__urd__": 256092,
98
+ "__uzn__": 256093,
99
+ "__vie__": 256094,
100
+ "__yor__": 256095,
101
+ "__yue__": 256096,
102
+ "__zlm__": 256097,
103
+ "__zul__": 256098
104
+ }
config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "SeamlessM4TModel"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 2,
13
+ "conv_depthwise_kernel_size": 31,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 8192,
16
+ "decoder_layerdrop": 0.05,
17
+ "decoder_layers": 24,
18
+ "decoder_start_token_id": 3,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 8192,
22
+ "encoder_layerdrop": 0.05,
23
+ "encoder_layers": 24,
24
+ "eos_token_id": 3,
25
+ "feature_projection_input_dim": 160,
26
+ "hidden_size": 1024,
27
+ "initializer_range": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "lang_embed_dim": 256,
30
+ "layer_norm_eps": 1e-05,
31
+ "leaky_relu_slope": 0.1,
32
+ "max_new_tokens": 256,
33
+ "max_position_embeddings": 1024,
34
+ "max_source_positions": 4096,
35
+ "model_type": "seamless_m4t",
36
+ "num_adapter_layers": 1,
37
+ "num_attention_heads": 16,
38
+ "num_conv_pos_embedding_groups": 16,
39
+ "num_conv_pos_embeddings": 128,
40
+ "num_hidden_layers": 24,
41
+ "pad_token_id": 0,
42
+ "position_embeddings_type": "relative",
43
+ "resblock_dilation_sizes": [
44
+ [
45
+ 1,
46
+ 3,
47
+ 5
48
+ ],
49
+ [
50
+ 1,
51
+ 3,
52
+ 5
53
+ ],
54
+ [
55
+ 1,
56
+ 3,
57
+ 5
58
+ ]
59
+ ],
60
+ "resblock_kernel_sizes": [
61
+ 3,
62
+ 7,
63
+ 11
64
+ ],
65
+ "rotary_embedding_base": 10000,
66
+ "sampling_rate": 16000,
67
+ "scale_embedding": true,
68
+ "speech_encoder_attention_heads": 16,
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
+ "spkr_embed_dim": 256,
75
+ "t2u_bos_token_id": 0,
76
+ "t2u_decoder_attention_heads": 16,
77
+ "t2u_decoder_ffn_dim": 8192,
78
+ "t2u_decoder_layers": 6,
79
+ "t2u_decoder_start_token_id": 2,
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_new_tokens": 1024,
85
+ "t2u_max_position_embeddings": 2048,
86
+ "t2u_pad_token_id": 1,
87
+ "t2u_vocab_size": 10082,
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.35.0.dev0",
90
+ "unit_embed_dim": 1280,
91
+ "unit_hifi_gan_vocab_size": 10000,
92
+ "upsample_initial_channel": 512,
93
+ "upsample_kernel_sizes": [
94
+ 11,
95
+ 8,
96
+ 8,
97
+ 4,
98
+ 4
99
+ ],
100
+ "upsample_rates": [
101
+ 5,
102
+ 4,
103
+ 4,
104
+ 2,
105
+ 2
106
+ ],
107
+ "use_cache": true,
108
+ "var_pred_dropout": 0.5,
109
+ "variance_predictor_kernel_size": 3,
110
+ "vocab_size": 256102,
111
+ "vocoder_num_langs": 36,
112
+ "vocoder_num_spkrs": 200,
113
+ "vocoder_offset": 4
114
+ }
generation_config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "decoder_start_token_id": 3,
4
+ "eos_token_id": 3,
5
+ "max_new_tokens": 256,
6
+ "pad_token_id": 0,
7
+ "t2u_lang_code_to_id": {
8
+ "arb": 10043,
9
+ "ben": 10044,
10
+ "cat": 10045,
11
+ "ces": 10046,
12
+ "cmn": 10047,
13
+ "cym": 10048,
14
+ "dan": 10049,
15
+ "deu": 10050,
16
+ "eng": 10051,
17
+ "est": 10052,
18
+ "fin": 10053,
19
+ "fra": 10054,
20
+ "hin": 10055,
21
+ "ind": 10056,
22
+ "ita": 10057,
23
+ "jpn": 10058,
24
+ "kan": 10059,
25
+ "kor": 10060,
26
+ "mlt": 10061,
27
+ "nld": 10062,
28
+ "pes": 10063,
29
+ "pol": 10064,
30
+ "por": 10065,
31
+ "ron": 10066,
32
+ "rus": 10067,
33
+ "slk": 10068,
34
+ "spa": 10069,
35
+ "swe": 10070,
36
+ "swh": 10071,
37
+ "tam": 10072,
38
+ "tel": 10073,
39
+ "tgl": 10074,
40
+ "tha": 10075,
41
+ "tur": 10076,
42
+ "ukr": 10077,
43
+ "urd": 10078,
44
+ "uzn": 10079,
45
+ "vie": 10080
46
+ },
47
+ "text_decoder_lang_to_code_id": {
48
+ "afr": 256001,
49
+ "amh": 256002,
50
+ "arb": 256003,
51
+ "ary": 256004,
52
+ "arz": 256005,
53
+ "asm": 256006,
54
+ "azj": 256007,
55
+ "bel": 256008,
56
+ "ben": 256009,
57
+ "bos": 256010,
58
+ "bul": 256011,
59
+ "cat": 256012,
60
+ "ceb": 256013,
61
+ "ces": 256014,
62
+ "ckb": 256015,
63
+ "cmn": 256016,
64
+ "cmn_Hant": 256017,
65
+ "cym": 256018,
66
+ "dan": 256019,
67
+ "deu": 256020,
68
+ "ell": 256021,
69
+ "eng": 256022,
70
+ "est": 256023,
71
+ "eus": 256024,
72
+ "fin": 256025,
73
+ "fra": 256026,
74
+ "fuv": 256027,
75
+ "gaz": 256028,
76
+ "gle": 256029,
77
+ "glg": 256030,
78
+ "guj": 256031,
79
+ "heb": 256032,
80
+ "hin": 256033,
81
+ "hrv": 256034,
82
+ "hun": 256035,
83
+ "hye": 256036,
84
+ "ibo": 256037,
85
+ "ind": 256038,
86
+ "isl": 256039,
87
+ "ita": 256040,
88
+ "jav": 256041,
89
+ "jpn": 256042,
90
+ "kan": 256043,
91
+ "kat": 256044,
92
+ "kaz": 256045,
93
+ "khk": 256046,
94
+ "khm": 256047,
95
+ "kir": 256048,
96
+ "kor": 256049,
97
+ "lao": 256050,
98
+ "lit": 256051,
99
+ "lug": 256052,
100
+ "luo": 256053,
101
+ "lvs": 256054,
102
+ "mai": 256055,
103
+ "mal": 256056,
104
+ "mar": 256057,
105
+ "mkd": 256058,
106
+ "mlt": 256059,
107
+ "mni": 256060,
108
+ "mya": 256061,
109
+ "nld": 256062,
110
+ "nno": 256063,
111
+ "nob": 256064,
112
+ "npi": 256065,
113
+ "nya": 256066,
114
+ "ory": 256067,
115
+ "pan": 256068,
116
+ "pbt": 256069,
117
+ "pes": 256070,
118
+ "pol": 256071,
119
+ "por": 256072,
120
+ "ron": 256073,
121
+ "rus": 256074,
122
+ "sat": 256075,
123
+ "slk": 256076,
124
+ "slv": 256077,
125
+ "sna": 256078,
126
+ "snd": 256079,
127
+ "som": 256080,
128
+ "spa": 256081,
129
+ "srp": 256082,
130
+ "swe": 256083,
131
+ "swh": 256084,
132
+ "tam": 256085,
133
+ "tel": 256086,
134
+ "tgk": 256087,
135
+ "tgl": 256088,
136
+ "tha": 256089,
137
+ "tur": 256090,
138
+ "ukr": 256091,
139
+ "urd": 256092,
140
+ "uzn": 256093,
141
+ "vie": 256094,
142
+ "yor": 256095,
143
+ "yue": 256096,
144
+ "zlm": 256097,
145
+ "zul": 256098
146
+ },
147
+ "transformers_version": "4.35.0.dev0",
148
+ "vocoder_lang_code_to_id": {
149
+ "arb": 0,
150
+ "ben": 1,
151
+ "cat": 2,
152
+ "ces": 3,
153
+ "cmn": 4,
154
+ "cym": 5,
155
+ "dan": 6,
156
+ "deu": 7,
157
+ "eng": 8,
158
+ "est": 9,
159
+ "fin": 10,
160
+ "fra": 11,
161
+ "hin": 12,
162
+ "ind": 13,
163
+ "ita": 14,
164
+ "jpn": 15,
165
+ "kor": 16,
166
+ "mlt": 17,
167
+ "nld": 18,
168
+ "pes": 19,
169
+ "pol": 20,
170
+ "por": 21,
171
+ "ron": 22,
172
+ "rus": 23,
173
+ "slk": 24,
174
+ "spa": 25,
175
+ "swe": 26,
176
+ "swh": 27,
177
+ "tel": 28,
178
+ "tgl": 29,
179
+ "tha": 30,
180
+ "tur": 31,
181
+ "ukr": 32,
182
+ "urd": 33,
183
+ "uzn": 34,
184
+ "vie": 35
185
+ }
186
+ }
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
+ }
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 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<pad>",
4
+ "<unk>",
5
+ "<s>",
6
+ "</s>",
7
+ "__afr__",
8
+ "__amh__",
9
+ "__arb__",
10
+ "__ary__",
11
+ "__arz__",
12
+ "__asm__",
13
+ "__azj__",
14
+ "__bel__",
15
+ "__ben__",
16
+ "__bos__",
17
+ "__bul__",
18
+ "__cat__",
19
+ "__ceb__",
20
+ "__ces__",
21
+ "__ckb__",
22
+ "__cmn__",
23
+ "__cmn_Hant__",
24
+ "__cym__",
25
+ "__dan__",
26
+ "__deu__",
27
+ "__ell__",
28
+ "__eng__",
29
+ "__est__",
30
+ "__eus__",
31
+ "__fin__",
32
+ "__fra__",
33
+ "__fuv__",
34
+ "__gaz__",
35
+ "__gle__",
36
+ "__glg__",
37
+ "__guj__",
38
+ "__heb__",
39
+ "__hin__",
40
+ "__hrv__",
41
+ "__hun__",
42
+ "__hye__",
43
+ "__ibo__",
44
+ "__ind__",
45
+ "__isl__",
46
+ "__ita__",
47
+ "__jav__",
48
+ "__jpn__",
49
+ "__kan__",
50
+ "__kat__",
51
+ "__kaz__",
52
+ "__khk__",
53
+ "__khm__",
54
+ "__kir__",
55
+ "__kor__",
56
+ "__lao__",
57
+ "__lit__",
58
+ "__lug__",
59
+ "__luo__",
60
+ "__lvs__",
61
+ "__mai__",
62
+ "__mal__",
63
+ "__mar__",
64
+ "__mkd__",
65
+ "__mlt__",
66
+ "__mni__",
67
+ "__mya__",
68
+ "__nld__",
69
+ "__nno__",
70
+ "__nob__",
71
+ "__npi__",
72
+ "__nya__",
73
+ "__ory__",
74
+ "__pan__",
75
+ "__pbt__",
76
+ "__pes__",
77
+ "__pol__",
78
+ "__por__",
79
+ "__ron__",
80
+ "__rus__",
81
+ "__sat__",
82
+ "__slk__",
83
+ "__slv__",
84
+ "__sna__",
85
+ "__snd__",
86
+ "__som__",
87
+ "__spa__",
88
+ "__srp__",
89
+ "__swe__",
90
+ "__swh__",
91
+ "__tam__",
92
+ "__tel__",
93
+ "__tgk__",
94
+ "__tgl__",
95
+ "__tha__",
96
+ "__tur__",
97
+ "__ukr__",
98
+ "__urd__",
99
+ "__uzn__",
100
+ "__vie__",
101
+ "__yor__",
102
+ "__yue__",
103
+ "__zlm__",
104
+ "__zul__"
105
+ ],
106
+ "bos_token": "<s>",
107
+ "cls_token": "<s>",
108
+ "eos_token": "</s>",
109
+ "pad_token": "<pad>",
110
+ "sep_token": "</s>",
111
+ "unk_token": "<unk>"
112
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "256002": {
44
+ "content": "__amh__",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "256003": {
52
+ "content": "__arb__",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "256004": {
60
+ "content": "__ary__",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "256005": {
68
+ "content": "__arz__",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "256006": {
76
+ "content": "__asm__",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "256007": {
84
+ "content": "__azj__",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "256008": {
92
+ "content": "__bel__",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "256009": {
100
+ "content": "__ben__",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "256010": {
108
+ "content": "__bos__",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "256011": {
116
+ "content": "__bul__",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "256012": {
124
+ "content": "__cat__",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "256013": {
132
+ "content": "__ceb__",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "256014": {
140
+ "content": "__ces__",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "256015": {
148
+ "content": "__ckb__",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "256016": {
156
+ "content": "__cmn__",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "256017": {
164
+ "content": "__cmn_Hant__",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "256018": {
172
+ "content": "__cym__",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "256019": {
180
+ "content": "__dan__",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "256020": {
188
+ "content": "__deu__",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "256021": {
196
+ "content": "__ell__",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "256022": {
204
+ "content": "__eng__",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "256023": {
212
+ "content": "__est__",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "256024": {
220
+ "content": "__eus__",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "256025": {
228
+ "content": "__fin__",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "256026": {
236
+ "content": "__fra__",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "256027": {
244
+ "content": "__fuv__",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "256028": {
252
+ "content": "__gaz__",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "256029": {
260
+ "content": "__gle__",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "256030": {
268
+ "content": "__glg__",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "256031": {
276
+ "content": "__guj__",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "256032": {
284
+ "content": "__heb__",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "256033": {
292
+ "content": "__hin__",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "256034": {
300
+ "content": "__hrv__",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "256035": {
308
+ "content": "__hun__",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "256036": {
316
+ "content": "__hye__",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "256037": {
324
+ "content": "__ibo__",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "256038": {
332
+ "content": "__ind__",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "256039": {
340
+ "content": "__isl__",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "256040": {
348
+ "content": "__ita__",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "256041": {
356
+ "content": "__jav__",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "256042": {
364
+ "content": "__jpn__",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "256043": {
372
+ "content": "__kan__",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "256044": {
380
+ "content": "__kat__",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "256045": {
388
+ "content": "__kaz__",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "256046": {
396
+ "content": "__khk__",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "256047": {
404
+ "content": "__khm__",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "256048": {
412
+ "content": "__kir__",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "256049": {
420
+ "content": "__kor__",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "256050": {
428
+ "content": "__lao__",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "256051": {
436
+ "content": "__lit__",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "256052": {
444
+ "content": "__lug__",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "256053": {
452
+ "content": "__luo__",
453
+ "lstrip": true,
454
+ "normalized": false,
455
+ "rstrip": true,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "256054": {
460
+ "content": "__lvs__",
461
+ "lstrip": true,
462
+ "normalized": false,
463
+ "rstrip": true,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "256055": {
468
+ "content": "__mai__",
469
+ "lstrip": true,
470
+ "normalized": false,
471
+ "rstrip": true,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "256056": {
476
+ "content": "__mal__",
477
+ "lstrip": true,
478
+ "normalized": false,
479
+ "rstrip": true,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "256057": {
484
+ "content": "__mar__",
485
+ "lstrip": true,
486
+ "normalized": false,
487
+ "rstrip": true,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "256058": {
492
+ "content": "__mkd__",
493
+ "lstrip": true,
494
+ "normalized": false,
495
+ "rstrip": true,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "256059": {
500
+ "content": "__mlt__",
501
+ "lstrip": true,
502
+ "normalized": false,
503
+ "rstrip": true,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "256060": {
508
+ "content": "__mni__",
509
+ "lstrip": true,
510
+ "normalized": false,
511
+ "rstrip": true,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "256061": {
516
+ "content": "__mya__",
517
+ "lstrip": true,
518
+ "normalized": false,
519
+ "rstrip": true,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "256062": {
524
+ "content": "__nld__",
525
+ "lstrip": true,
526
+ "normalized": false,
527
+ "rstrip": true,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "256063": {
532
+ "content": "__nno__",
533
+ "lstrip": true,
534
+ "normalized": false,
535
+ "rstrip": true,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "256064": {
540
+ "content": "__nob__",
541
+ "lstrip": true,
542
+ "normalized": false,
543
+ "rstrip": true,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "256065": {
548
+ "content": "__npi__",
549
+ "lstrip": true,
550
+ "normalized": false,
551
+ "rstrip": true,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "256066": {
556
+ "content": "__nya__",
557
+ "lstrip": true,
558
+ "normalized": false,
559
+ "rstrip": true,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "256067": {
564
+ "content": "__ory__",
565
+ "lstrip": true,
566
+ "normalized": false,
567
+ "rstrip": true,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "256068": {
572
+ "content": "__pan__",
573
+ "lstrip": true,
574
+ "normalized": false,
575
+ "rstrip": true,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "256069": {
580
+ "content": "__pbt__",
581
+ "lstrip": true,
582
+ "normalized": false,
583
+ "rstrip": true,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "256070": {
588
+ "content": "__pes__",
589
+ "lstrip": true,
590
+ "normalized": false,
591
+ "rstrip": true,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "256071": {
596
+ "content": "__pol__",
597
+ "lstrip": true,
598
+ "normalized": false,
599
+ "rstrip": true,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "256072": {
604
+ "content": "__por__",
605
+ "lstrip": true,
606
+ "normalized": false,
607
+ "rstrip": true,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "256073": {
612
+ "content": "__ron__",
613
+ "lstrip": true,
614
+ "normalized": false,
615
+ "rstrip": true,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "256074": {
620
+ "content": "__rus__",
621
+ "lstrip": true,
622
+ "normalized": false,
623
+ "rstrip": true,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "256075": {
628
+ "content": "__sat__",
629
+ "lstrip": true,
630
+ "normalized": false,
631
+ "rstrip": true,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "256076": {
636
+ "content": "__slk__",
637
+ "lstrip": true,
638
+ "normalized": false,
639
+ "rstrip": true,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "256077": {
644
+ "content": "__slv__",
645
+ "lstrip": true,
646
+ "normalized": false,
647
+ "rstrip": true,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "256078": {
652
+ "content": "__sna__",
653
+ "lstrip": true,
654
+ "normalized": false,
655
+ "rstrip": true,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "256079": {
660
+ "content": "__snd__",
661
+ "lstrip": true,
662
+ "normalized": false,
663
+ "rstrip": true,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "256080": {
668
+ "content": "__som__",
669
+ "lstrip": true,
670
+ "normalized": false,
671
+ "rstrip": true,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "256081": {
676
+ "content": "__spa__",
677
+ "lstrip": true,
678
+ "normalized": false,
679
+ "rstrip": true,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "256082": {
684
+ "content": "__srp__",
685
+ "lstrip": true,
686
+ "normalized": false,
687
+ "rstrip": true,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "256083": {
692
+ "content": "__swe__",
693
+ "lstrip": true,
694
+ "normalized": false,
695
+ "rstrip": true,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "256084": {
700
+ "content": "__swh__",
701
+ "lstrip": true,
702
+ "normalized": false,
703
+ "rstrip": true,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "256085": {
708
+ "content": "__tam__",
709
+ "lstrip": true,
710
+ "normalized": false,
711
+ "rstrip": true,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "256086": {
716
+ "content": "__tel__",
717
+ "lstrip": true,
718
+ "normalized": false,
719
+ "rstrip": true,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "256087": {
724
+ "content": "__tgk__",
725
+ "lstrip": true,
726
+ "normalized": false,
727
+ "rstrip": true,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "256088": {
732
+ "content": "__tgl__",
733
+ "lstrip": true,
734
+ "normalized": false,
735
+ "rstrip": true,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "256089": {
740
+ "content": "__tha__",
741
+ "lstrip": true,
742
+ "normalized": false,
743
+ "rstrip": true,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "256090": {
748
+ "content": "__tur__",
749
+ "lstrip": true,
750
+ "normalized": false,
751
+ "rstrip": true,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "256091": {
756
+ "content": "__ukr__",
757
+ "lstrip": true,
758
+ "normalized": false,
759
+ "rstrip": true,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "256092": {
764
+ "content": "__urd__",
765
+ "lstrip": true,
766
+ "normalized": false,
767
+ "rstrip": true,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "256093": {
772
+ "content": "__uzn__",
773
+ "lstrip": true,
774
+ "normalized": false,
775
+ "rstrip": true,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "256094": {
780
+ "content": "__vie__",
781
+ "lstrip": true,
782
+ "normalized": false,
783
+ "rstrip": true,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "256095": {
788
+ "content": "__yor__",
789
+ "lstrip": true,
790
+ "normalized": false,
791
+ "rstrip": true,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "256096": {
796
+ "content": "__yue__",
797
+ "lstrip": true,
798
+ "normalized": false,
799
+ "rstrip": true,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "256097": {
804
+ "content": "__zlm__",
805
+ "lstrip": true,
806
+ "normalized": false,
807
+ "rstrip": true,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "256098": {
812
+ "content": "__zul__",
813
+ "lstrip": true,
814
+ "normalized": false,
815
+ "rstrip": true,
816
+ "single_word": false,
817
+ "special": true
818
+ }
819
+ },
820
+ "additional_special_tokens": [
821
+ "<pad>",
822
+ "<unk>",
823
+ "<s>",
824
+ "</s>",
825
+ "__afr__",
826
+ "__amh__",
827
+ "__arb__",
828
+ "__ary__",
829
+ "__arz__",
830
+ "__asm__",
831
+ "__azj__",
832
+ "__bel__",
833
+ "__ben__",
834
+ "__bos__",
835
+ "__bul__",
836
+ "__cat__",
837
+ "__ceb__",
838
+ "__ces__",
839
+ "__ckb__",
840
+ "__cmn__",
841
+ "__cmn_Hant__",
842
+ "__cym__",
843
+ "__dan__",
844
+ "__deu__",
845
+ "__ell__",
846
+ "__eng__",
847
+ "__est__",
848
+ "__eus__",
849
+ "__fin__",
850
+ "__fra__",
851
+ "__fuv__",
852
+ "__gaz__",
853
+ "__gle__",
854
+ "__glg__",
855
+ "__guj__",
856
+ "__heb__",
857
+ "__hin__",
858
+ "__hrv__",
859
+ "__hun__",
860
+ "__hye__",
861
+ "__ibo__",
862
+ "__ind__",
863
+ "__isl__",
864
+ "__ita__",
865
+ "__jav__",
866
+ "__jpn__",
867
+ "__kan__",
868
+ "__kat__",
869
+ "__kaz__",
870
+ "__khk__",
871
+ "__khm__",
872
+ "__kir__",
873
+ "__kor__",
874
+ "__lao__",
875
+ "__lit__",
876
+ "__lug__",
877
+ "__luo__",
878
+ "__lvs__",
879
+ "__mai__",
880
+ "__mal__",
881
+ "__mar__",
882
+ "__mkd__",
883
+ "__mlt__",
884
+ "__mni__",
885
+ "__mya__",
886
+ "__nld__",
887
+ "__nno__",
888
+ "__nob__",
889
+ "__npi__",
890
+ "__nya__",
891
+ "__ory__",
892
+ "__pan__",
893
+ "__pbt__",
894
+ "__pes__",
895
+ "__pol__",
896
+ "__por__",
897
+ "__ron__",
898
+ "__rus__",
899
+ "__sat__",
900
+ "__slk__",
901
+ "__slv__",
902
+ "__sna__",
903
+ "__snd__",
904
+ "__som__",
905
+ "__spa__",
906
+ "__srp__",
907
+ "__swe__",
908
+ "__swh__",
909
+ "__tam__",
910
+ "__tel__",
911
+ "__tgk__",
912
+ "__tgl__",
913
+ "__tha__",
914
+ "__tur__",
915
+ "__ukr__",
916
+ "__urd__",
917
+ "__uzn__",
918
+ "__vie__",
919
+ "__yor__",
920
+ "__yue__",
921
+ "__zlm__",
922
+ "__zul__"
923
+ ],
924
+ "bos_token": "<s>",
925
+ "clean_up_tokenization_spaces": true,
926
+ "cls_token": "<s>",
927
+ "eos_token": "</s>",
928
+ "model_max_length": 1000000000000000019884624838656,
929
+ "pad_token": "<pad>",
930
+ "processor_class": "SeamlessM4TProcessor",
931
+ "sep_token": "</s>",
932
+ "sp_model_kwargs": {},
933
+ "src_lang": "__eng__",
934
+ "tgt_lang": "__fra__",
935
+ "tokenizer_class": "SeamlessM4TTokenizer",
936
+ "tokenizer_file": null,
937
+ "unk_token": "<unk>"
938
+ }