Hugging Face's logo

cdactvm
/
w2v-assames

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Inference Endpoints
Model card Files Community
cdactvm commited on
Commit
d08b0f5
•
1 Parent(s): c704440

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +112 -0
  2. preprocessor_config.json +10 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer_config.json +14 -0
  6. vocab.json +68 -0
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "adapter_attn_dim": null,
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": 0.1,
12
+ "bos_token": "<s>",
13
+ "bos_token_id": 0,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_lower_case": true,
49
+ "do_stable_layer_norm": false,
50
+ "eos_token": "</s>",
51
+ "eos_token_id": 2,
52
+ "feat_extract_activation": "gelu",
53
+ "feat_extract_norm": "group",
54
+ "feat_proj_dropout": 0.0,
55
+ "feat_quantizer_dropout": 0.0,
56
+ "final_dropout": 0.1,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 768,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_feature_length": 10,
65
+ "mask_feature_min_masks": 0,
66
+ "mask_feature_prob": 0.0,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_masks": 2,
69
+ "mask_time_prob": 0.05,
70
+ "model_type": "wav2vec2",
71
+ "num_adapter_layers": 3,
72
+ "num_attention_heads": 12,
73
+ "num_codevector_groups": 2,
74
+ "num_codevectors_per_group": 320,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 12,
79
+ "num_negatives": 100,
80
+ "output_hidden_size": 768,
81
+ "pad_token": "[PAD]",
82
+ "pad_token_id": 1,
83
+ "proj_codevector_dim": 256,
84
+ "tdnn_dilation": [
85
+ 1,
86
+ 2,
87
+ 3,
88
+ 1,
89
+ 1
90
+ ],
91
+ "tdnn_dim": [
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 512,
96
+ 1500
97
+ ],
98
+ "tdnn_kernel": [
99
+ 5,
100
+ 3,
101
+ 3,
102
+ 1,
103
+ 1
104
+ ],
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.30.2",
107
+ "unk_token": "[UNK]",
108
+ "use_weighted_layer_sum": false,
109
+ "vocab_size": 66,
110
+ "word_delimiter_token": ".",
111
+ "xvector_output_dim": 512
112
+ }
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": false,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:738150020607ec51c38946649016d54851e5e9db2f1f4098801d35f981e47e53
3
+ size 377758487
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "target_lang": null,
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "unk_token": "<unk>",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<pad>": 1,
4
+ "<s>": 0,
5
+ "<unk>": 3,
6
+ "|": 4,
7
+ "ঁ": 5,
8
+ "ং": 6,
9
+ "ঃ": 7,
10
+ "অ": 8,
11
+ "আ": 9,
12
+ "ই": 10,
13
+ "ঈ": 11,
14
+ "উ": 12,
15
+ "ঊ": 13,
16
+ "ঋ": 14,
17
+ "এ": 15,
18
+ "ঐ": 16,
19
+ "ও": 17,
20
+ "ঔ": 18,
21
+ "ক": 19,
22
+ "খ": 20,
23
+ "গ": 21,
24
+ "ঘ": 22,
25
+ "ঙ": 23,
26
+ "চ": 24,
27
+ "ছ": 25,
28
+ "জ": 26,
29
+ "ঝ": 27,
30
+ "ঞ": 28,
31
+ "ট": 29,
32
+ "ঠ": 30,
33
+ "ড": 31,
34
+ "ঢ": 32,
35
+ "ণ": 33,
36
+ "ত": 34,
37
+ "থ": 35,
38
+ "দ": 36,
39
+ "ধ": 37,
40
+ "ন": 38,
41
+ "প": 39,
42
+ "ফ": 40,
43
+ "ব": 41,
44
+ "ভ": 42,
45
+ "ম": 43,
46
+ "য": 44,
47
+ "র": 45,
48
+ "ল": 46,
49
+ "শ": 47,
50
+ "ষ": 48,
51
+ "স": 49,
52
+ "হ": 50,
53
+ "়": 51,
54
+ "া": 52,
55
+ "ি": 53,
56
+ "ী": 54,
57
+ "ু": 55,
58
+ "ূ": 56,
59
+ "ৃ": 57,
60
+ "ে": 58,
61
+ "ৈ": 59,
62
+ "ো": 60,
63
+ "ৌ": 61,
64
+ "্": 62,
65
+ "ৎ": 63,
66
+ "ৰ": 64,
67
+ "ৱ": 65
68
+ }