Hugging Face's logo

anish-shilpakar
/
nepali-wav2vec-v2

Model card Files Community
anish-shilpakar commited on
Commit
71c8584
•
1 Parent(s): b830b2b

Added 90 and 91 models and processors

Browse files
Files changed (14) hide show
  1. models/model_wav2vec_90/config.json +115 -0
  2. models/model_wav2vec_90/preprocessor_config.json +10 -0
  3. models/model_wav2vec_90/training_args.bin +3 -0
  4. models/trained_model_91/config.json +115 -0
  5. models/trained_model_91/preprocessor_config.json +9 -0
  6. models/trained_model_91/training_args.bin +3 -0
  7. processors/processor_91/preprocessor_config.json +10 -0
  8. processors/processor_91/special_tokens_map.json +6 -0
  9. processors/processor_91/tokenizer_config.json +11 -0
  10. processors/processor_91/vocab.json +65 -0
  11. processors/processor_wav2vec_90/preprocessor_config.json +10 -0
  12. processors/processor_wav2vec_90/special_tokens_map.json +6 -0
  13. processors/processor_wav2vec_90/tokenizer_config.json +12 -0
  14. processors/processor_wav2vec_90/vocab.json +65 -0
models/model_wav2vec_90/config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "anish-shilpakar/wav2vec2-nepali-asr-v1",
3
+ "activation_dropout": 0.0,
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": 0.12,
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": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.12,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.1,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.05,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "num_adapter_layers": 3,
78
+ "num_attention_heads": 16,
79
+ "num_codevector_groups": 2,
80
+ "num_codevectors_per_group": 320,
81
+ "num_conv_pos_embedding_groups": 16,
82
+ "num_conv_pos_embeddings": 128,
83
+ "num_feat_extract_layers": 7,
84
+ "num_hidden_layers": 24,
85
+ "num_negatives": 100,
86
+ "output_hidden_size": 1024,
87
+ "pad_token_id": 62,
88
+ "proj_codevector_dim": 768,
89
+ "tdnn_dilation": [
90
+ 1,
91
+ 2,
92
+ 3,
93
+ 1,
94
+ 1
95
+ ],
96
+ "tdnn_dim": [
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 1500
102
+ ],
103
+ "tdnn_kernel": [
104
+ 5,
105
+ 3,
106
+ 3,
107
+ 1,
108
+ 1
109
+ ],
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.26.0",
112
+ "use_weighted_layer_sum": false,
113
+ "vocab_size": 63,
114
+ "xvector_output_dim": 512
115
+ }
models/model_wav2vec_90/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
+ }
models/model_wav2vec_90/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73892696d45cf8565329284ac8566d935d43f87b8841ec2f385e742000f006f
3
+ size 3451
models/trained_model_91/config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "anish-shilpakar/wav2vec2-nepali-asr-v1",
3
+ "activation_dropout": 0.0,
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": 0.12,
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": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.12,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.1,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.05,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "num_adapter_layers": 3,
78
+ "num_attention_heads": 16,
79
+ "num_codevector_groups": 2,
80
+ "num_codevectors_per_group": 320,
81
+ "num_conv_pos_embedding_groups": 16,
82
+ "num_conv_pos_embeddings": 128,
83
+ "num_feat_extract_layers": 7,
84
+ "num_hidden_layers": 24,
85
+ "num_negatives": 100,
86
+ "output_hidden_size": 1024,
87
+ "pad_token_id": 62,
88
+ "proj_codevector_dim": 768,
89
+ "tdnn_dilation": [
90
+ 1,
91
+ 2,
92
+ 3,
93
+ 1,
94
+ 1
95
+ ],
96
+ "tdnn_dim": [
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 1500
102
+ ],
103
+ "tdnn_kernel": [
104
+ 5,
105
+ 3,
106
+ 3,
107
+ 1,
108
+ 1
109
+ ],
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.20.1",
112
+ "use_weighted_layer_sum": false,
113
+ "vocab_size": 63,
114
+ "xvector_output_dim": 512
115
+ }
models/trained_model_91/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": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
models/trained_model_91/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1953e1552f7565a275a289bfaae8458a6c00a890b6ef6dee05278229cb550e7c
3
+ size 3311
processors/processor_91/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
+ }
processors/processor_91/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
+ }
processors/processor_91/tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "pad_token": "[PAD]",
6
+ "processor_class": "Wav2Vec2Processor",
7
+ "replace_word_delimiter_char": " ",
8
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
9
+ "unk_token": "[UNK]",
10
+ "word_delimiter_token": "|"
11
+ }
processors/processor_91/vocab.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 62,
3
+ "[UNK]": 61,
4
+ "|": 43,
5
+ "ँ": 46,
6
+ "ं": 54,
7
+ "ः": 37,
8
+ "अ": 40,
9
+ "आ": 51,
10
+ "इ": 30,
11
+ "ई": 0,
12
+ "उ": 42,
13
+ "ऊ": 24,
14
+ "ऋ": 55,
15
+ "ए": 14,
16
+ "ऐ": 45,
17
+ "ओ": 31,
18
+ "औ": 2,
19
+ "क": 12,
20
+ "ख": 4,
21
+ "ग": 58,
22
+ "घ": 39,
23
+ "ङ": 25,
24
+ "च": 60,
25
+ "छ": 19,
26
+ "ज": 48,
27
+ "झ": 1,
28
+ "ञ": 15,
29
+ "ट": 11,
30
+ "ठ": 22,
31
+ "ड": 50,
32
+ "ढ": 8,
33
+ "ण": 57,
34
+ "त": 33,
35
+ "थ": 13,
36
+ "द": 6,
37
+ "ध": 7,
38
+ "न": 27,
39
+ "प": 20,
40
+ "फ": 17,
41
+ "ब": 28,
42
+ "भ": 21,
43
+ "म": 59,
44
+ "य": 23,
45
+ "र": 16,
46
+ "ल": 3,
47
+ "व": 32,
48
+ "श": 38,
49
+ "ष": 34,
50
+ "स": 41,
51
+ "ह": 49,
52
+ "ा": 26,
53
+ "ि": 35,
54
+ "ी": 36,
55
+ "ु": 18,
56
+ "ू": 52,
57
+ "ृ": 56,
58
+ "े": 44,
59
+ "ै": 9,
60
+ "ो": 10,
61
+ "ौ": 29,
62
+ "्": 47,
63
+ "।": 53,
64
+ "‍": 5
65
+ }
processors/processor_wav2vec_90/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
+ }
processors/processor_wav2vec_90/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
+ }
processors/processor_wav2vec_90/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "[PAD]",
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "replace_word_delimiter_char": " ",
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
processors/processor_wav2vec_90/vocab.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 62,
3
+ "[UNK]": 61,
4
+ "|": 43,
5
+ "ँ": 46,
6
+ "ं": 54,
7
+ "ः": 37,
8
+ "अ": 40,
9
+ "आ": 51,
10
+ "इ": 30,
11
+ "ई": 0,
12
+ "उ": 42,
13
+ "ऊ": 24,
14
+ "ऋ": 55,
15
+ "ए": 14,
16
+ "ऐ": 45,
17
+ "ओ": 31,
18
+ "औ": 2,
19
+ "क": 12,
20
+ "ख": 4,
21
+ "ग": 58,
22
+ "घ": 39,
23
+ "ङ": 25,
24
+ "च": 60,
25
+ "छ": 19,
26
+ "ज": 48,
27
+ "झ": 1,
28
+ "ञ": 15,
29
+ "ट": 11,
30
+ "ठ": 22,
31
+ "ड": 50,
32
+ "ढ": 8,
33
+ "ण": 57,
34
+ "त": 33,
35
+ "थ": 13,
36
+ "द": 6,
37
+ "ध": 7,
38
+ "न": 27,
39
+ "प": 20,
40
+ "फ": 17,
41
+ "ब": 28,
42
+ "भ": 21,
43
+ "म": 59,
44
+ "य": 23,
45
+ "र": 16,
46
+ "ल": 3,
47
+ "व": 32,
48
+ "श": 38,
49
+ "ष": 34,
50
+ "स": 41,
51
+ "ह": 49,
52
+ "ा": 26,
53
+ "ि": 35,
54
+ "ी": 36,
55
+ "ु": 18,
56
+ "ू": 52,
57
+ "ृ": 56,
58
+ "े": 44,
59
+ "ै": 9,
60
+ "ो": 10,
61
+ "ौ": 29,
62
+ "्": 47,
63
+ "।": 53,
64
+ "‍": 5
65
+ }