Hugging Face's logo

omaryshchenko
/
w2v-bert-2.0-english-CV16.1-v1-onnx

Automatic Speech Recognition
Transformers
ONNX
wav2vec2-bert
Inference Endpoints
Model card Files Community
Oleksii Maryshchenko commited on
Commit
5aaae01
·
1 Parent(s): 41ab1a7

configs

Browse files
Files changed (8) hide show
  1. added_tokens.json +4 -0
  2. config.json +81 -0
  3. preprocessor_config.json +11 -0
  4. quantize_config.json +120 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer.json +81 -0
  7. tokenizer_config.json +48 -0
  8. vocab.json +32 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 31,
3
+ "<s>": 30
4
+ }
config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "omaryshchenko/w2v-bert-2.0-english-CV16.1-v1",
3
+ "activation_dropout": 0.0,
4
+ "adapter_act": "relu",
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": true,
8
+ "apply_spec_augment": false,
9
+ "architectures": [
10
+ "Wav2Vec2BertForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 768,
15
+ "codevector_dim": 768,
16
+ "conformer_conv_dropout": 0.1,
17
+ "contrastive_logits_temperature": 0.1,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "ctc_loss_reduction": "mean",
20
+ "ctc_zero_infinity": true,
21
+ "diversity_loss_weight": 0.1,
22
+ "eos_token_id": 2,
23
+ "feat_proj_dropout": 0.0,
24
+ "feat_quantizer_dropout": 0.0,
25
+ "feature_projection_input_dim": 160,
26
+ "final_dropout": 0.1,
27
+ "hidden_act": "swish",
28
+ "hidden_dropout": 0.0,
29
+ "hidden_size": 1024,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "layer_norm_eps": 1e-05,
33
+ "layerdrop": 0.1,
34
+ "left_max_position_embeddings": 64,
35
+ "mask_feature_length": 10,
36
+ "mask_feature_min_masks": 0,
37
+ "mask_feature_prob": 0.0,
38
+ "mask_time_length": 10,
39
+ "mask_time_min_masks": 2,
40
+ "mask_time_prob": 0.05,
41
+ "max_source_positions": 5000,
42
+ "model_type": "wav2vec2-bert",
43
+ "num_adapter_layers": 1,
44
+ "num_attention_heads": 16,
45
+ "num_codevector_groups": 2,
46
+ "num_codevectors_per_group": 320,
47
+ "num_hidden_layers": 24,
48
+ "num_negatives": 100,
49
+ "output_hidden_size": 1024,
50
+ "pad_token_id": 29,
51
+ "position_embeddings_type": "relative_key",
52
+ "proj_codevector_dim": 768,
53
+ "right_max_position_embeddings": 8,
54
+ "rotary_embedding_base": 10000,
55
+ "tdnn_dilation": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 1,
60
+ 1
61
+ ],
62
+ "tdnn_dim": [
63
+ 512,
64
+ 512,
65
+ 512,
66
+ 512,
67
+ 1500
68
+ ],
69
+ "tdnn_kernel": [
70
+ 5,
71
+ 3,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "transformers_version": "4.39.3",
77
+ "use_intermediate_ffn_before_adapter": false,
78
+ "use_weighted_layer_sum": false,
79
+ "vocab_size": 32,
80
+ "xvector_output_dim": 512
81
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 1,
7
+ "processor_class": "Wav2Vec2BertProcessor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000,
10
+ "stride": 2
11
+ }
quantize_config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fp16": {},
3
+ "q8": {
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Add",
8
+ "Cast",
9
+ "Clip",
10
+ "Concat",
11
+ "Constant",
12
+ "ConstantOfShape",
13
+ "Conv",
14
+ "Div",
15
+ "Einsum",
16
+ "Gather",
17
+ "LayerNormalization",
18
+ "MatMul",
19
+ "Mul",
20
+ "Pad",
21
+ "Range",
22
+ "Relu",
23
+ "Reshape",
24
+ "Shape",
25
+ "Sigmoid",
26
+ "Slice",
27
+ "Softmax",
28
+ "Split",
29
+ "Sub",
30
+ "Transpose",
31
+ "Unsqueeze"
32
+ ],
33
+ "weight_type": "QUInt8"
34
+ }
35
+ },
36
+ "per_channel": true,
37
+ "reduce_range": true
38
+ },
39
+ "int8": {
40
+ "per_model_config": {
41
+ "model": {
42
+ "op_types": [
43
+ "Add",
44
+ "Cast",
45
+ "Clip",
46
+ "Concat",
47
+ "Constant",
48
+ "ConstantOfShape",
49
+ "Conv",
50
+ "Div",
51
+ "Einsum",
52
+ "Gather",
53
+ "LayerNormalization",
54
+ "MatMul",
55
+ "Mul",
56
+ "Pad",
57
+ "Range",
58
+ "Relu",
59
+ "Reshape",
60
+ "Shape",
61
+ "Sigmoid",
62
+ "Slice",
63
+ "Softmax",
64
+ "Split",
65
+ "Sub",
66
+ "Transpose",
67
+ "Unsqueeze"
68
+ ],
69
+ "weight_type": "QInt8"
70
+ }
71
+ },
72
+ "per_channel": true,
73
+ "reduce_range": true
74
+ },
75
+ "uint8": {
76
+ "per_model_config": {
77
+ "model": {
78
+ "op_types": [
79
+ "Add",
80
+ "Cast",
81
+ "Clip",
82
+ "Concat",
83
+ "Constant",
84
+ "ConstantOfShape",
85
+ "Conv",
86
+ "Div",
87
+ "Einsum",
88
+ "Gather",
89
+ "LayerNormalization",
90
+ "MatMul",
91
+ "Mul",
92
+ "Pad",
93
+ "Range",
94
+ "Relu",
95
+ "Reshape",
96
+ "Shape",
97
+ "Sigmoid",
98
+ "Slice",
99
+ "Softmax",
100
+ "Split",
101
+ "Sub",
102
+ "Transpose",
103
+ "Unsqueeze"
104
+ ],
105
+ "weight_type": "QUInt8"
106
+ }
107
+ },
108
+ "per_channel": true,
109
+ "reduce_range": true
110
+ },
111
+ "q4": {
112
+ "block_size": 32,
113
+ "is_symmetric": true,
114
+ "accuracy_level": null
115
+ },
116
+ "bnb4": {
117
+ "block_size": 64,
118
+ "quant_type": 1
119
+ }
120
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 29,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": true,
11
+ "rstrip": true,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 28,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": true,
20
+ "rstrip": true,
21
+ "normalized": false,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": {
26
+ "type": "Replace",
27
+ "pattern": {
28
+ "String": " "
29
+ },
30
+ "content": "|"
31
+ },
32
+ "pre_tokenizer": {
33
+ "type": "Split",
34
+ "pattern": {
35
+ "Regex": ""
36
+ },
37
+ "behavior": "Isolated",
38
+ "invert": false
39
+ },
40
+ "post_processor": null,
41
+ "decoder": {
42
+ "type": "CTC",
43
+ "pad_token": "[PAD]",
44
+ "word_delimiter_token": "|",
45
+ "cleanup": true
46
+ },
47
+ "model": {
48
+ "vocab": {
49
+ "'": 1,
50
+ "[PAD]": 29,
51
+ "[UNK]": 28,
52
+ "a": 2,
53
+ "b": 3,
54
+ "c": 4,
55
+ "d": 5,
56
+ "e": 6,
57
+ "f": 7,
58
+ "g": 8,
59
+ "h": 9,
60
+ "i": 10,
61
+ "j": 11,
62
+ "k": 12,
63
+ "l": 13,
64
+ "m": 14,
65
+ "n": 15,
66
+ "o": 16,
67
+ "p": 17,
68
+ "q": 18,
69
+ "r": 19,
70
+ "s": 20,
71
+ "t": 21,
72
+ "u": 22,
73
+ "v": 23,
74
+ "w": 24,
75
+ "x": 25,
76
+ "y": 26,
77
+ "z": 27,
78
+ "|": 0
79
+ }
80
+ }
81
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "28": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "29": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "30": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "31": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "processor_class": "Wav2Vec2BertProcessor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 1,
3
+ "[PAD]": 29,
4
+ "[UNK]": 28,
5
+ "a": 2,
6
+ "b": 3,
7
+ "c": 4,
8
+ "d": 5,
9
+ "e": 6,
10
+ "f": 7,
11
+ "g": 8,
12
+ "h": 9,
13
+ "i": 10,
14
+ "j": 11,
15
+ "k": 12,
16
+ "l": 13,
17
+ "m": 14,
18
+ "n": 15,
19
+ "o": 16,
20
+ "p": 17,
21
+ "q": 18,
22
+ "r": 19,
23
+ "s": 20,
24
+ "t": 21,
25
+ "u": 22,
26
+ "v": 23,
27
+ "w": 24,
28
+ "x": 25,
29
+ "y": 26,
30
+ "z": 27,
31
+ "|": 0
32
+ }