Hugging Face's logo

tsobolev
/
indic-wav2vec-benagli-finetuned14-1

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Inference Endpoints
Model card Files Community
tsobolev commited on
Commit
68a78a9
•
1 Parent(s): 44b9f4b

Training in progress step 50

Browse files
Files changed (6) hide show
  1. config.json +110 -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 +89 -0
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/input/indic-wav2vec-accel-v14/indic-wav2vec-benagli-finetuned14",
3
+ "activation_dropout": 0.1,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.0,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 1024,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 4096,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.0,
65
+ "mask_feature_length": 10,
66
+ "mask_feature_min_masks": 0,
67
+ "mask_feature_prob": 0.0,
68
+ "mask_time_length": 10,
69
+ "mask_time_min_masks": 2,
70
+ "mask_time_prob": 0.05,
71
+ "model_type": "wav2vec2",
72
+ "num_adapter_layers": 3,
73
+ "num_attention_heads": 16,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 24,
80
+ "num_negatives": 100,
81
+ "output_hidden_size": 1024,
82
+ "pad_token_id": 0,
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": "4.33.2",
107
+ "use_weighted_layer_sum": false,
108
+ "vocab_size": 87,
109
+ "xvector_output_dim": 512
110
+ }
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 sha256:87167c80681fe9beac1ab11092a23137b9418dc32bddbf8e3f35f44015c6f65e
3
+ size 1262258541
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 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "3": 5,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "F": 17,
8
+ "e": 32,
9
+ "i": 65,
10
+ "l": 76,
11
+ "|": 62,
12
+ "ঁ": 86,
13
+ "ং": 26,
14
+ "ঃ": 29,
15
+ "অ": 18,
16
+ "আ": 48,
17
+ "ই": 4,
18
+ "ঈ": 42,
19
+ "উ": 14,
20
+ "ঊ": 40,
21
+ "ঋ": 43,
22
+ "এ": 46,
23
+ "ঐ": 52,
24
+ "ও": 19,
25
+ "ঔ": 67,
26
+ "ক": 79,
27
+ "খ": 21,
28
+ "গ": 28,
29
+ "ঘ": 72,
30
+ "ঙ": 70,
31
+ "চ": 37,
32
+ "ছ": 49,
33
+ "জ": 78,
34
+ "ঝ": 75,
35
+ "ঞ": 16,
36
+ "ট": 20,
37
+ "ঠ": 44,
38
+ "ড": 55,
39
+ "ঢ": 85,
40
+ "ণ": 57,
41
+ "ত": 45,
42
+ "থ": 31,
43
+ "দ": 73,
44
+ "ধ": 13,
45
+ "ন": 80,
46
+ "প": 53,
47
+ "ফ": 58,
48
+ "ব": 51,
49
+ "ভ": 68,
50
+ "ম": 25,
51
+ "য": 81,
52
+ "র": 83,
53
+ "ল": 8,
54
+ "শ": 38,
55
+ "ষ": 34,
56
+ "স": 23,
57
+ "হ": 6,
58
+ "়": 36,
59
+ "া": 15,
60
+ "ি": 33,
61
+ "ী": 54,
62
+ "ু": 59,
63
+ "ূ": 50,
64
+ "ৃ": 60,
65
+ "ে": 82,
66
+ "ৈ": 10,
67
+ "ো": 11,
68
+ "ৌ": 27,
69
+ "্": 9,
70
+ "ৎ": 71,
71
+ "ৗ": 39,
72
+ "ড়": 22,
73
+ "য়": 77,
74
+ "০": 24,
75
+ "১": 61,
76
+ "২": 74,
77
+ "৩": 84,
78
+ "৪": 12,
79
+ "৫": 47,
80
+ "৬": 41,
81
+ "৭": 56,
82
+ "৮": 63,
83
+ "৯": 35,
84
+ "ৰ": 66,
85
+ "‌": 30,
86
+ "‍": 64,
87
+ "‎": 69,
88
+ "…": 7
89
+ }