Hugging Face's logo

rohitp1
/
subh_w2lm_base_distill_noisy_teacher_mozilla_epochs_50_batch_16

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wavlm
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
rohitp1 commited on
Commit
3eabb5c
•
1 Parent(s): a00c567

Training in progress, step 250

Browse files
Files changed (9) hide show
  1. .gitignore +1 -0
  2. config.json +122 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. runs/May31_12-11-36_node1.iisc.ac.in/1685520907.901139/events.out.tfevents.1685520907.node1.iisc.ac.in.18741.1 +3 -0
  6. runs/May31_12-11-36_node1.iisc.ac.in/events.out.tfevents.1685520907.node1.iisc.ac.in.18741.0 +3 -0
  7. runs/May31_20-36-43_node1.iisc.ac.in/1685550639.5554867/events.out.tfevents.1685550639.node1.iisc.ac.in.102126.1 +3 -0
  8. runs/May31_20-36-43_node1.iisc.ac.in/events.out.tfevents.1685550639.node1.iisc.ac.in.102126.0 +3 -0
  9. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rohitp1/ws_w2lm_base_plus_finetune_teacher_noise_mozilla_100_epochs_batch_8",
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
+ "WavLMForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
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": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.0,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
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
+ "max_bucket_distance": 800,
77
+ "model_type": "wavlm",
78
+ "no_mask_channel_overlap": false,
79
+ "no_mask_time_overlap": false,
80
+ "num_adapter_layers": 3,
81
+ "num_attention_heads": 12,
82
+ "num_buckets": 320,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_ctc_classes": 80,
88
+ "num_feat_extract_layers": 7,
89
+ "num_hidden_layers": 12,
90
+ "num_negatives": 100,
91
+ "output_hidden_size": 768,
92
+ "pad_token_id": 28,
93
+ "proj_codevector_dim": 256,
94
+ "replace_prob": 0.5,
95
+ "tdnn_dilation": [
96
+ 1,
97
+ 2,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "tdnn_dim": [
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 512,
107
+ 1500
108
+ ],
109
+ "tdnn_kernel": [
110
+ 5,
111
+ 3,
112
+ 3,
113
+ 1,
114
+ 1
115
+ ],
116
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
117
+ "torch_dtype": "float32",
118
+ "transformers_version": "4.29.2",
119
+ "use_weighted_layer_sum": false,
120
+ "vocab_size": 31,
121
+ "xvector_output_dim": 512
122
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9a83afc1b944a3c07ecc25395dd0d9dad703902c00d1210e152f665aeacb15
3
+ size 377706061
runs/May31_12-11-36_node1.iisc.ac.in/1685520907.901139/events.out.tfevents.1685520907.node1.iisc.ac.in.18741.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8381211ddfbfac3407a08aebad2d239fdbe27f5955bb3e0cb261d10abd6058e3
3
+ size 6073
runs/May31_12-11-36_node1.iisc.ac.in/events.out.tfevents.1685520907.node1.iisc.ac.in.18741.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df2e62053ba8154f7d640f3f6268f370bb7e8f9f88ec1dcced747443c1ad63c
3
+ size 6211
runs/May31_20-36-43_node1.iisc.ac.in/1685550639.5554867/events.out.tfevents.1685550639.node1.iisc.ac.in.102126.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5130e08ed948b6290a637d0837c2ec092243d652fa6083186ea0fe80c9a1fcd9
3
+ size 6073
runs/May31_20-36-43_node1.iisc.ac.in/events.out.tfevents.1685550639.node1.iisc.ac.in.102126.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53785ccd958bafb043017db5b12f3f622002140a7620b09f760f14690fdc38b6
3
+ size 6686
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485ed65492ad037e6e2b3eac6e8c6d5304f46b24fe97a18cbd328f7dc552dd03
3
+ size 4079