Hugging Face's logo

rahulraj1406
/
Wav2vec2-Raj

Safetensors
wav2vec2
Model card Files
xet
 Community
rahulraj1406 commited on
Commit
af0b237
·
verified ·
1 Parent(s): 80fc5f8

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .ipynb_checkpoints/added_tokens-checkpoint.json +4 -0
  2. .ipynb_checkpoints/config-checkpoint.json +109 -0
  3. .ipynb_checkpoints/processor_config-checkpoint.json +12 -0
  4. .ipynb_checkpoints/tokenizer_config-checkpoint.json +56 -0
  5. added_tokens.json +4 -0
  6. config.json +109 -0
  7. model.safetensors +3 -0
  8. preprocessor_config.json +9 -0
  9. processor_config.json +12 -0
  10. tokenizer_config.json +56 -0
  11. training_args.bin +3 -0
  12. vocab.json +69 -0
.ipynb_checkpoints/added_tokens-checkpoint.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 68,
3
+ "<s>": 67
4
+ }
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
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_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": true,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "dtype": "float32",
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
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
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": 0.1,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_masks": 2,
69
+ "mask_time_prob": 0.1,
70
+ "model_type": "wav2vec2",
71
+ "num_adapter_layers": 3,
72
+ "num_attention_heads": 16,
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": 24,
79
+ "num_negatives": 100,
80
+ "output_hidden_size": 1024,
81
+ "pad_token_id": 66,
82
+ "proj_codevector_dim": 768,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "transformers_version": "5.12.1",
105
+ "use_cache": false,
106
+ "use_weighted_layer_sum": false,
107
+ "vocab_size": 67,
108
+ "xvector_output_dim": 512
109
+ }
.ipynb_checkpoints/processor_config-checkpoint.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "do_normalize": true,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ },
11
+ "processor_class": "Wav2Vec2Processor"
12
+ }
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "64": {
4
+ "content": "|",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "65": {
12
+ "content": "[UNK]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "66": {
20
+ "content": "[PAD]",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "67": {
28
+ "content": "<s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "68": {
36
+ "content": "</s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "backend": "custom",
45
+ "bos_token": "<s>",
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
+ }
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 68,
3
+ "<s>": 67
4
+ }
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
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_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": true,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "dtype": "float32",
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
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
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": 0.1,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_masks": 2,
69
+ "mask_time_prob": 0.1,
70
+ "model_type": "wav2vec2",
71
+ "num_adapter_layers": 3,
72
+ "num_attention_heads": 16,
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": 24,
79
+ "num_negatives": 100,
80
+ "output_hidden_size": 1024,
81
+ "pad_token_id": 66,
82
+ "proj_codevector_dim": 768,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "transformers_version": "5.12.1",
105
+ "use_cache": false,
106
+ "use_weighted_layer_sum": false,
107
+ "vocab_size": 67,
108
+ "xvector_output_dim": 512
109
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:320d4bdf871317c0bf2db91b897be4e0379a4470f7cd4006090c4a88c5ee6557
3
+ size 1262082132
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
processor_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "do_normalize": true,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ },
11
+ "processor_class": "Wav2Vec2Processor"
12
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "64": {
4
+ "content": "|",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "65": {
12
+ "content": "[UNK]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "66": {
20
+ "content": "[PAD]",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "67": {
28
+ "content": "<s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "68": {
36
+ "content": "</s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "backend": "custom",
45
+ "bos_token": "<s>",
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:e04fd4cf6616054b84ad29049693fd3b41b10bb527fb10cf1c9fc993c87fd3cd
3
+ size 5201
vocab.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 66,
3
+ "[UNK]": 65,
4
+ "|": 64,
5
+ "ం": 0,
6
+ "ః": 1,
7
+ "అ": 2,
8
+ "ఆ": 3,
9
+ "ఇ": 4,
10
+ "ఈ": 5,
11
+ "ఉ": 6,
12
+ "ఊ": 7,
13
+ "ఋ": 8,
14
+ "ఎ": 9,
15
+ "ఏ": 10,
16
+ "ఐ": 11,
17
+ "ఒ": 12,
18
+ "ఓ": 13,
19
+ "ఔ": 14,
20
+ "క": 15,
21
+ "ఖ": 16,
22
+ "గ": 17,
23
+ "ఘ": 18,
24
+ "ఙ": 19,
25
+ "చ": 20,
26
+ "ఛ": 21,
27
+ "జ": 22,
28
+ "ఝ": 23,
29
+ "ఞ": 24,
30
+ "ట": 25,
31
+ "ఠ": 26,
32
+ "డ": 27,
33
+ "ఢ": 28,
34
+ "ణ": 29,
35
+ "త": 30,
36
+ "థ": 31,
37
+ "ద": 32,
38
+ "ధ": 33,
39
+ "న": 34,
40
+ "ప": 35,
41
+ "ఫ": 36,
42
+ "బ": 37,
43
+ "భ": 38,
44
+ "మ": 39,
45
+ "య": 40,
46
+ "ర": 41,
47
+ "ల": 42,
48
+ "ళ": 43,
49
+ "వ": 44,
50
+ "శ": 45,
51
+ "ష": 46,
52
+ "స": 47,
53
+ "హ": 48,
54
+ "ా": 49,
55
+ "ి": 50,
56
+ "ీ": 51,
57
+ "ు": 52,
58
+ "ూ": 53,
59
+ "ృ": 54,
60
+ "ె": 55,
61
+ "ే": 56,
62
+ "ై": 57,
63
+ "ొ": 58,
64
+ "ో": 59,
65
+ "ౌ": 60,
66
+ "్": 61,
67
+ "ౖ": 62,
68
+ "౦": 63
69
+ }