Hugging Face's logo

gopikachu
/
whisper-small-hi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
gopikachu commited on
Commit
801dc67
•
1 Parent(s): bf51886

Training in progress, step 50

Browse files
Files changed (9) hide show
  1. config.json +134 -64
  2. model.safetensors +2 -2
  3. preprocessor_config.json +10 -7
  4. runs/Jun01_16-48-57_dn001/events.out.tfevents.1717246139.dn001.984470.2 +2 -2
  5. runs/Jun01_17-02-28_dn001/events.out.tfevents.1717246950.dn001.984470.3 +3 -0
  6. runs/Jun01_20-55-43_dn001/events.out.tfevents.1717260951.dn001.984470.22 +3 -0
  7. runs/Jun01_20-56-28_dn001/events.out.tfevents.1717260989.dn001.984470.23 +3 -0
  8. runs/Jun01_20-58-34_dn001/events.out.tfevents.1717261116.dn001.984470.24 +3 -0
  9. training_args.bin +2 -2
config.json CHANGED
@@ -1,82 +1,152 @@
1
  {
2
- "_name_or_path": "facebook/w2v-bert-2.0",
3
  "activation_dropout": 0.0,
4
- "adapter_act": "relu",
5
- "adapter_kernel_size": 3,
6
- "adapter_stride": 2,
7
- "add_adapter": true,
8
  "apply_spec_augment": false,
9
  "architectures": [
10
- "Wav2Vec2BertForCTC"
11
  ],
12
  "attention_dropout": 0.0,
13
- "bos_token_id": 1,
14
- "classifier_proj_size": 768,
15
- "codevector_dim": 768,
16
- "conformer_conv_dropout": 0.1,
17
- "contrastive_logits_temperature": 0.1,
18
- "conv_depthwise_kernel_size": 31,
19
- "ctc_loss_reduction": "mean",
20
- "ctc_zero_infinity": false,
21
- "diversity_loss_weight": 0.1,
22
- "eos_token_id": 2,
23
- "feat_proj_dropout": 0.0,
24
- "feat_quantizer_dropout": 0.0,
25
- "feature_projection_input_dim": 160,
26
- "final_dropout": 0.1,
27
- "hidden_act": "swish",
28
- "hidden_dropout": 0.0,
29
- "hidden_size": 1024,
30
- "initializer_range": 0.02,
31
- "intermediate_size": 4096,
32
- "layer_norm_eps": 1e-05,
33
- "layerdrop": 0.0,
34
- "left_max_position_embeddings": 64,
 
 
 
 
 
 
 
 
 
 
 
 
35
  "mask_feature_length": 10,
36
  "mask_feature_min_masks": 0,
37
  "mask_feature_prob": 0.0,
38
  "mask_time_length": 10,
39
  "mask_time_min_masks": 2,
40
- "mask_time_prob": 0.0,
41
- "max_source_positions": 5000,
42
- "model_type": "wav2vec2-bert",
43
- "num_adapter_layers": 1,
44
- "num_attention_heads": 16,
45
- "num_codevector_groups": 2,
46
- "num_codevectors_per_group": 320,
47
- "num_hidden_layers": 24,
48
- "num_negatives": 100,
49
- "output_hidden_size": 1024,
50
- "pad_token_id": 14,
51
- "position_embeddings_type": "relative_key",
52
- "proj_codevector_dim": 768,
53
- "right_max_position_embeddings": 8,
54
- "rotary_embedding_base": 10000,
55
- "tdnn_dilation": [
56
  1,
57
  2,
58
- 3,
59
- 1,
60
- 1
61
- ],
62
- "tdnn_dim": [
63
- 512,
64
- 512,
65
- 512,
66
- 512,
67
- 1500
68
- ],
69
- "tdnn_kernel": [
70
- 5,
71
- 3,
72
- 3,
73
- 1,
74
- 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  ],
76
  "torch_dtype": "float32",
77
  "transformers_version": "4.41.1",
78
- "use_intermediate_ffn_before_adapter": false,
79
  "use_weighted_layer_sum": false,
80
- "vocab_size": 17,
81
- "xvector_output_dim": 512
82
  }
 
1
  {
2
+ "_name_or_path": "openai/whisper-small",
3
  "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
 
 
 
5
  "apply_spec_augment": false,
6
  "architectures": [
7
+ "WhisperForConditionalGeneration"
8
  ],
9
  "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
  "mask_feature_length": 10,
45
  "mask_feature_min_masks": 0,
46
  "mask_feature_prob": 0.0,
47
  "mask_time_length": 10,
48
  "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 12,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
 
 
 
 
 
60
  1,
61
  2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50360,
144
+ 50361,
145
+ 50362
146
  ],
147
  "torch_dtype": "float32",
148
  "transformers_version": "4.41.1",
149
+ "use_cache": true,
150
  "use_weighted_layer_sum": false,
151
+ "vocab_size": 51865
 
152
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:594874eb0f7c44449ace15783df7baef4e67935884a768920d5ceba64bce0115
3
- size 2422884252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d0053fec7d2ff91df7018c85770a50e04b7e4a4eda31c2659b1ec68231ad2d
3
+ size 966995080
preprocessor_config.json CHANGED
@@ -1,11 +1,14 @@
1
  {
2
- "feature_extractor_type": "SeamlessM4TFeatureExtractor",
 
3
  "feature_size": 80,
4
- "num_mel_bins": 80,
 
 
 
5
  "padding_side": "right",
6
- "padding_value": 1,
7
- "processor_class": "Wav2Vec2BertProcessor",
8
- "return_attention_mask": true,
9
- "sampling_rate": 16000,
10
- "stride": 2
11
  }
 
1
  {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
  "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
  "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
 
14
  }
runs/Jun01_16-48-57_dn001/events.out.tfevents.1717246139.dn001.984470.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d480e6d099076f87fbc1693afaff5c2fbf1a7924d21a75bdad7959ff59ae837
3
- size 13336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff1f9a97d4e3035b8805182f4c8807d3e2a4e968e2758ae18155de20c2a83eb
3
+ size 15024
runs/Jun01_17-02-28_dn001/events.out.tfevents.1717246950.dn001.984470.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:237d27d838e97358c4cf0127d2a5894e956d35e253a4814267d83e1a6d6413c8
3
+ size 8578
runs/Jun01_20-55-43_dn001/events.out.tfevents.1717260951.dn001.984470.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b093145f956f4a82069cc755587fdd424779733d3efe6e8dea1c3886a3f2e0
3
+ size 6576
runs/Jun01_20-56-28_dn001/events.out.tfevents.1717260989.dn001.984470.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532d4283859101fa1139f7e10d40606b4f486b2df035cf7d0cfaea9342fd4520
3
+ size 6783
runs/Jun01_20-58-34_dn001/events.out.tfevents.1717261116.dn001.984470.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c52a79e2590a5eef0941bb4b3544d3949c1c4ac3febef1a3a15886cff4f10e
3
+ size 7139
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ced86ba208755db4360e15b144b19529e1d21ed980204e83101764ad038626e9
3
- size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ea57f454930a6f5742ccd50c1aaba7148845b2cdc85c9788eb93390cb35d31
3
+ size 5240