Chahat7874 commited on
Commit
ff9b6cb
1 Parent(s): 85ad082

Training in progress, step 145

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 111,
3
+ "<s>": 110,
4
+ "[PAD]": 109
5
+ }
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": 16,
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": 0.1,
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": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
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_channel_length": 10,
64
+ "mask_channel_min_space": 1,
65
+ "mask_channel_other": 0.0,
66
+ "mask_channel_prob": 0.0,
67
+ "mask_channel_selection": "static",
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_min_space": 1,
74
+ "mask_time_other": 0.0,
75
+ "mask_time_prob": 0.05,
76
+ "mask_time_selection": "static",
77
+ "model_type": "wav2vec2",
78
+ "num_adapter_layers": 3,
79
+ "num_attention_heads": 16,
80
+ "num_codevector_groups": 2,
81
+ "num_codevectors_per_group": 320,
82
+ "num_conv_pos_embedding_groups": 16,
83
+ "num_conv_pos_embeddings": 128,
84
+ "num_feat_extract_layers": 7,
85
+ "num_hidden_layers": 24,
86
+ "num_negatives": 100,
87
+ "output_hidden_size": 1024,
88
+ "pad_token_id": 109,
89
+ "proj_codevector_dim": 768,
90
+ "tdnn_dilation": [
91
+ 1,
92
+ 2,
93
+ 3,
94
+ 1,
95
+ 1
96
+ ],
97
+ "tdnn_dim": [
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 1500
103
+ ],
104
+ "tdnn_kernel": [
105
+ 5,
106
+ 3,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.42.0.dev0",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 112,
115
+ "xvector_output_dim": 512
116
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23879e5385cc35c7b7cc588102757ed976d5265397d766540ccd87bd3f0f2b51
3
+ size 1265726848
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
+ }
runs/Jun13_13-51-19_aabe1f53a52a/events.out.tfevents.1718286793.aabe1f53a52a.4826.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d8423f5fd41d492dbfff97b4ec4976909048d3588cc5609404be4a06ae9211
3
+ size 7257
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_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "108": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "109": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "110": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "111": {
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": "Wav2Vec2Processor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": "hi",
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86fa7f589cf470e3eaed04489732aaf8a55ba6ef1b8d2511f2a7faf6453663cc
3
+ size 5176
vocab.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hi": {
3
+ "!": 1,
4
+ "\"": 2,
5
+ "&": 3,
6
+ "'": 4,
7
+ ",": 5,
8
+ "-": 6,
9
+ ".": 7,
10
+ ":": 8,
11
+ "?": 9,
12
+ "[PAD]": 109,
13
+ "[UNK]": 108,
14
+ "a": 10,
15
+ "b": 11,
16
+ "c": 12,
17
+ "d": 13,
18
+ "e": 14,
19
+ "f": 15,
20
+ "g": 16,
21
+ "h": 17,
22
+ "i": 18,
23
+ "j": 19,
24
+ "k": 20,
25
+ "l": 21,
26
+ "m": 22,
27
+ "n": 23,
28
+ "o": 24,
29
+ "p": 25,
30
+ "q": 26,
31
+ "r": 27,
32
+ "s": 28,
33
+ "t": 29,
34
+ "u": 30,
35
+ "v": 31,
36
+ "w": 32,
37
+ "x": 33,
38
+ "y": 34,
39
+ "z": 35,
40
+ "|": 0,
41
+ "ँ": 37,
42
+ "ं": 38,
43
+ "ः": 39,
44
+ "अ": 40,
45
+ "आ": 41,
46
+ "इ": 42,
47
+ "ई": 43,
48
+ "उ": 44,
49
+ "ऊ": 45,
50
+ "ऋ": 46,
51
+ "ए": 47,
52
+ "ऐ": 48,
53
+ "ऑ": 49,
54
+ "ओ": 50,
55
+ "औ": 51,
56
+ "क": 52,
57
+ "ख": 53,
58
+ "ग": 54,
59
+ "घ": 55,
60
+ "च": 56,
61
+ "छ": 57,
62
+ "ज": 58,
63
+ "झ": 59,
64
+ "ञ": 60,
65
+ "ट": 61,
66
+ "ठ": 62,
67
+ "ड": 63,
68
+ "ढ": 64,
69
+ "ण": 65,
70
+ "त": 66,
71
+ "थ": 67,
72
+ "द": 68,
73
+ "ध": 69,
74
+ "न": 70,
75
+ "प": 71,
76
+ "फ": 72,
77
+ "ब": 73,
78
+ "भ": 74,
79
+ "म": 75,
80
+ "य": 76,
81
+ "र": 77,
82
+ "ल": 78,
83
+ "व": 79,
84
+ "श": 80,
85
+ "ष": 81,
86
+ "स": 82,
87
+ "ह": 83,
88
+ "़": 84,
89
+ "ा": 85,
90
+ "ि": 86,
91
+ "ी": 87,
92
+ "ु": 88,
93
+ "ू": 89,
94
+ "ृ": 90,
95
+ "ॅ": 91,
96
+ "े": 92,
97
+ "ै": 93,
98
+ "ॉ": 94,
99
+ "ो": 95,
100
+ "ौ": 96,
101
+ "्": 97,
102
+ "क़": 98,
103
+ "ग़": 99,
104
+ "ज़": 100,
105
+ "ड़": 101,
106
+ "ढ़": 102,
107
+ "फ़": 103,
108
+ "।": 104,
109
+ "‘": 105,
110
+ "’": 106,
111
+ "“": 107,
112
+ "”": 108
113
+ }
114
+ }