Hugging Face's logo

SumitMdhr
/
Model_17.2

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
SumitMdhr commited on
Commit
5160331
•
1 Parent(s): 021df88

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +116 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. preprocessor_config.json +10 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +101 -0
  8. training_args.bin +3 -0
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": null,
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": 0.0,
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": 0.1,
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": 68,
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": "4.37.2",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 71,
115
+ "xvector_output_dim": 512
116
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f3b07b5bcd28fe1408f658363219baa8235d0b1b83833812035f7dd40eb224
3
+ size 1262098580
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5458ae60896766afaaaf9bcee2f27df3bdd10f86999190f95c269974ebcf0ca9
3
+ size 2490741942
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
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbbacc8085a9d05d3021cdb64d77578aa12d308f7cffb7c474baee2d7a7e2f83
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d253cc5d8a14fe1e7ec92fa84674f677025d7bbb106c6f3cd336c2a65d1d3c9
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3883848786354065,
3
+ "best_model_checkpoint": "./model/checkpoint-4252",
4
+ "epoch": 4.999412110523222,
5
+ "eval_steps": 500,
6
+ "global_step": 4252,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 0.0002850705882352941,
14
+ "loss": 2.6138,
15
+ "step": 850
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_cer": 0.27268008948545863,
20
+ "eval_cer_best": 0.7273199105145414,
21
+ "eval_loss": 0.7238138318061829,
22
+ "eval_runtime": 95.5312,
23
+ "eval_samples_per_second": 31.665,
24
+ "eval_steps_per_second": 3.967,
25
+ "step": 850
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 0.0002700705882352941,
30
+ "loss": 1.0825,
31
+ "step": 1701
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_cer": 0.2253959731543624,
36
+ "eval_cer_best": 0.7746040268456376,
37
+ "eval_loss": 0.5289922952651978,
38
+ "eval_runtime": 95.2118,
39
+ "eval_samples_per_second": 31.771,
40
+ "eval_steps_per_second": 3.981,
41
+ "step": 1701
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "learning_rate": 0.0002550882352941176,
46
+ "loss": 0.9076,
47
+ "step": 2551
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "eval_cer": 0.20298881431767338,
52
+ "eval_cer_best": 0.7970111856823267,
53
+ "eval_loss": 0.46624556183815,
54
+ "eval_runtime": 94.6631,
55
+ "eval_samples_per_second": 31.955,
56
+ "eval_steps_per_second": 4.004,
57
+ "step": 2551
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "learning_rate": 0.00024008823529411761,
62
+ "loss": 0.804,
63
+ "step": 3402
64
+ },
65
+ {
66
+ "epoch": 4.0,
67
+ "eval_cer": 0.18314093959731545,
68
+ "eval_cer_best": 0.8168590604026845,
69
+ "eval_loss": 0.42872071266174316,
70
+ "eval_runtime": 94.4283,
71
+ "eval_samples_per_second": 32.035,
72
+ "eval_steps_per_second": 4.014,
73
+ "step": 3402
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "learning_rate": 0.00022510588235294114,
78
+ "loss": 0.7448,
79
+ "step": 4252
80
+ },
81
+ {
82
+ "epoch": 5.0,
83
+ "eval_cer": 0.1720626398210291,
84
+ "eval_cer_best": 0.8279373601789709,
85
+ "eval_loss": 0.3883848786354065,
86
+ "eval_runtime": 94.0362,
87
+ "eval_samples_per_second": 32.168,
88
+ "eval_steps_per_second": 4.03,
89
+ "step": 4252
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 17000,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 20,
96
+ "save_steps": 500,
97
+ "total_flos": 6.943311650462615e+18,
98
+ "train_batch_size": 16,
99
+ "trial_name": null,
100
+ "trial_params": null
101
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d398ad809cb783d30c4a7d7ac689f7da78023bf3c209a6c688256d9d8c50c3b
3
+ size 4664