Hugging Face's logo

suggisingh
/
xlsr_hindi_LMless

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Inference Endpoints
Model card Files Metrics Community
suggisingh commited on
Commit
07b3482
•
1 Parent(s): c6dce5e

Training in progress, step 100

Browse files
Files changed (9) hide show
  1. added_tokens.json +6 -0
  2. config.json +108 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +10 -0
  5. runs/May07_09-46-01_c61596324c89/events.out.tfevents.1715075228.c61596324c89.570.0 +3 -0
  6. special_tokens_map.json +6 -0
  7. tokenizer_config.json +56 -0
  8. training_args.bin +3 -0
  9. vocab.json +131 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 130,
3
+ "<s>": 129,
4
+ "PAD": 131,
5
+ "[PAD]": 128
6
+ }
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.0,
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": 768,
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": 0.0,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.0,
58
+ "hidden_size": 1024,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
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": 24,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1024,
80
+ "pad_token_id": 131,
81
+ "proj_codevector_dim": 768,
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": "4.40.1",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 132,
107
+ "xvector_output_dim": 512
108
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e27967c1ec21b3f5f8121209054f7a4437ba214cad51016460b27967ecfd5c8b
3
+ size 1262348680
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": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
runs/May07_09-46-01_c61596324c89/events.out.tfevents.1715075228.c61596324c89.570.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f8e9bd992dced42835640e6261995ecc5082e7bef163c17865e3d81d31d72a3
3
+ size 6096
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "127": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "128": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "129": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "130": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "131": {
36
+ "content": "PAD",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "do_lower_case": false,
47
+ "eos_token": "</s>",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "PAD",
50
+ "processor_class": "Wav2Vec2Processor",
51
+ "replace_word_delimiter_char": " ",
52
+ "target_lang": null,
53
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
54
+ "unk_token": "[UNK]",
55
+ "word_delimiter_token": "|"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cccbde3f93e7bb1d526108597db9cbe4b703b79076b592340bbdbd358c7a731
3
+ size 4984
vocab.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 1,
3
+ "\"": 2,
4
+ "&": 3,
5
+ "'": 4,
6
+ ",": 5,
7
+ "-": 6,
8
+ ".": 7,
9
+ ":": 8,
10
+ "?": 9,
11
+ "A": 10,
12
+ "B": 11,
13
+ "C": 12,
14
+ "D": 13,
15
+ "E": 14,
16
+ "F": 15,
17
+ "G": 16,
18
+ "I": 17,
19
+ "J": 18,
20
+ "K": 19,
21
+ "L": 20,
22
+ "M": 21,
23
+ "N": 22,
24
+ "O": 23,
25
+ "P": 24,
26
+ "R": 25,
27
+ "S": 26,
28
+ "T": 27,
29
+ "V": 28,
30
+ "W": 29,
31
+ "X": 30,
32
+ "Y": 31,
33
+ "Z": 32,
34
+ "[PAD]": 128,
35
+ "[UNK]": 127,
36
+ "a": 33,
37
+ "b": 34,
38
+ "c": 35,
39
+ "d": 36,
40
+ "e": 37,
41
+ "f": 38,
42
+ "g": 39,
43
+ "h": 40,
44
+ "i": 41,
45
+ "j": 42,
46
+ "k": 43,
47
+ "l": 44,
48
+ "m": 45,
49
+ "n": 46,
50
+ "o": 47,
51
+ "p": 48,
52
+ "r": 49,
53
+ "s": 50,
54
+ "t": 51,
55
+ "u": 52,
56
+ "v": 53,
57
+ "w": 54,
58
+ "x": 55,
59
+ "y": 56,
60
+ "z": 57,
61
+ "|": 0,
62
+ "ँ": 59,
63
+ "ं": 60,
64
+ "ः": 61,
65
+ "अ": 62,
66
+ "आ": 63,
67
+ "इ": 64,
68
+ "ई": 65,
69
+ "उ": 66,
70
+ "ऊ": 67,
71
+ "ऋ": 68,
72
+ "ए": 69,
73
+ "ऐ": 70,
74
+ "ऑ": 71,
75
+ "ओ": 72,
76
+ "औ": 73,
77
+ "क": 74,
78
+ "ख": 75,
79
+ "ग": 76,
80
+ "घ": 77,
81
+ "च": 78,
82
+ "छ": 79,
83
+ "ज": 80,
84
+ "झ": 81,
85
+ "ञ": 82,
86
+ "ट": 83,
87
+ "ठ": 84,
88
+ "ड": 85,
89
+ "ढ": 86,
90
+ "ण": 87,
91
+ "त": 88,
92
+ "थ": 89,
93
+ "द": 90,
94
+ "ध": 91,
95
+ "न": 92,
96
+ "प": 93,
97
+ "फ": 94,
98
+ "ब": 95,
99
+ "भ": 96,
100
+ "म": 97,
101
+ "य": 98,
102
+ "र": 99,
103
+ "ल": 100,
104
+ "व": 101,
105
+ "श": 102,
106
+ "ष": 103,
107
+ "स": 104,
108
+ "ह": 105,
109
+ "़": 106,
110
+ "ा": 107,
111
+ "ि": 108,
112
+ "ी": 109,
113
+ "ु": 110,
114
+ "ू": 111,
115
+ "ृ": 112,
116
+ "ॅ": 113,
117
+ "े": 114,
118
+ "ै": 115,
119
+ "ॉ": 116,
120
+ "ो": 117,
121
+ "ौ": 118,
122
+ "्": 119,
123
+ "ख़": 120,
124
+ "ज़": 121,
125
+ "ड़": 122,
126
+ "ढ़": 123,
127
+ "।": 124,
128
+ "–": 125,
129
+ "‘": 126,
130
+ "’": 127
131
+ }