Hugging Face's logo

facebook
/
mms-1b-fl102

Automatic Speech Recognition
Transformers
PyTorch
Safetensors
wav2vec2
mms
Inference Endpoints
Model card Files Community
5
patrickvonplaten commited on
Commit
f3e9673
•
1 Parent(s): 06b7bd1

upload weights

Browse files
Files changed (6) hide show
  1. config.json +108 -0
  2. preprocessor_config.json +10 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer_config.json +13 -0
  6. vocab.json +80 -0
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-1b",
3
+ "activation_dropout": 0.05,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.05,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 1024,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.05,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.05,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.05,
57
+ "hidden_size": 1280,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 5120,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.05,
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.05,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_attn_adapters": 1,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 48,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1280,
80
+ "pad_token_id": 0,
81
+ "proj_codevector_dim": 1024,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.30.0.dev0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 78,
107
+ "xvector_output_dim": 512
108
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add79ca4d36b63ff0289a16966c4544db4e1e107e9882eb02cc500ce9c552e9b
3
+ size 3859360653
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "<unk>",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 75,
3
+ "\"": 62,
4
+ "$": 48,
5
+ "%": 47,
6
+ "&": 57,
7
+ "'": 31,
8
+ "+": 56,
9
+ ",": 44,
10
+ "-": 32,
11
+ ".": 37,
12
+ "/": 45,
13
+ "0": 27,
14
+ "1": 30,
15
+ "2": 35,
16
+ "3": 41,
17
+ "4": 39,
18
+ "5": 38,
19
+ "6": 40,
20
+ "7": 43,
21
+ "8": 42,
22
+ "9": 36,
23
+ ":": 46,
24
+ ";": 52,
25
+ "</s>": 2,
26
+ "<pad>": 0,
27
+ "<s>": 1,
28
+ "<unk>": 3,
29
+ "[": 59,
30
+ "]": 60,
31
+ "a": 7,
32
+ "b": 24,
33
+ "c": 16,
34
+ "d": 15,
35
+ "e": 5,
36
+ "f": 19,
37
+ "g": 21,
38
+ "h": 13,
39
+ "i": 9,
40
+ "j": 29,
41
+ "k": 26,
42
+ "l": 14,
43
+ "m": 18,
44
+ "n": 10,
45
+ "o": 8,
46
+ "p": 20,
47
+ "q": 34,
48
+ "r": 12,
49
+ "s": 11,
50
+ "t": 6,
51
+ "u": 17,
52
+ "v": 25,
53
+ "w": 23,
54
+ "x": 28,
55
+ "y": 22,
56
+ "z": 33,
57
+ "|": 4,
58
+ "£": 68,
59
+ "¥": 53,
60
+ "°": 58,
61
+ "²": 76,
62
+ "á": 49,
63
+ "ã": 66,
64
+ "ç": 64,
65
+ "é": 55,
66
+ "í": 50,
67
+ "ó": 67,
68
+ "õ": 69,
69
+ "ö": 74,
70
+ "ú": 70,
71
+ "ü": 54,
72
+ "ł": 73,
73
+ "̇": 77,
74
+ "​": 71,
75
+ "–": 61,
76
+ "—": 51,
77
+ "‘": 72,
78
+ "’": 65,
79
+ "”": 63
80
+ }