Hugging Face's logo

Aspik101
/
tanmoyio-wav2vec2-large-xlsr-bengali_checkpoint-2700_5626

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Inference Endpoints
Model card Files Community
Aspik101 commited on
Commit
195b2a9
•
1 Parent(s): 9d58f4b

Hubert commit

Browse files
Files changed (8) hide show
  1. config.json +116 -0
  2. optimizer.pt +3 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +160 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tanmoyio/wav2vec2-large-xlsr-bengali",
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": 256,
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": true,
47
+ "diversity_loss_weight": 100,
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": 118,
89
+ "proj_codevector_dim": 256,
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": "4.31.0",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 121,
115
+ "xvector_output_dim": 512
116
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ed87b42ea3af3e19c738aadfead3f8528201736a86dc493fc952ee849bcafd
3
+ size 2491053125
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1df09bd924c5620c1d99e00cc4e3853136fb42c1e2638d6d96b80780d9a37d7
3
+ size 1262397933
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8942410b5fe6ddf12514b31ed43766419df02fab62c9cfedd4e573e372d759e
3
+ size 14639
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:259afe9c7e24c4783a07c89f5160ce998b874e9dcf9e916ad37a5b349256a88d
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9780746917145943,
3
+ "best_model_checkpoint": "models_ft/tanmoyio/checkpoint-2700",
4
+ "epoch": 2.8830752802989856,
5
+ "global_step": 2700,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 1.794e-06,
13
+ "loss": 14.2834,
14
+ "step": 300
15
+ },
16
+ {
17
+ "epoch": 0.32,
18
+ "eval_loss": 11.77846622467041,
19
+ "eval_runtime": 152.5322,
20
+ "eval_samples_per_second": 25.057,
21
+ "eval_steps_per_second": 3.134,
22
+ "eval_wer": 0.9999748850993294,
23
+ "eval_wer_clean": 0.9999748850993294,
24
+ "step": 300
25
+ },
26
+ {
27
+ "epoch": 0.64,
28
+ "learning_rate": 3.5940000000000002e-06,
29
+ "loss": 7.221,
30
+ "step": 600
31
+ },
32
+ {
33
+ "epoch": 0.64,
34
+ "eval_loss": 4.340027809143066,
35
+ "eval_runtime": 150.288,
36
+ "eval_samples_per_second": 25.431,
37
+ "eval_steps_per_second": 3.181,
38
+ "eval_wer": 0.9999748850993294,
39
+ "eval_wer_clean": 0.9999748850993294,
40
+ "step": 600
41
+ },
42
+ {
43
+ "epoch": 0.96,
44
+ "learning_rate": 5.3939999999999995e-06,
45
+ "loss": 3.983,
46
+ "step": 900
47
+ },
48
+ {
49
+ "epoch": 0.96,
50
+ "eval_loss": 3.630129814147949,
51
+ "eval_runtime": 149.1255,
52
+ "eval_samples_per_second": 25.629,
53
+ "eval_steps_per_second": 3.205,
54
+ "eval_wer": 0.9999748850993294,
55
+ "eval_wer_clean": 0.9999748850993294,
56
+ "step": 900
57
+ },
58
+ {
59
+ "epoch": 1.28,
60
+ "learning_rate": 7.194000000000001e-06,
61
+ "loss": 3.5338,
62
+ "step": 1200
63
+ },
64
+ {
65
+ "epoch": 1.28,
66
+ "eval_loss": 3.402911901473999,
67
+ "eval_runtime": 150.143,
68
+ "eval_samples_per_second": 25.456,
69
+ "eval_steps_per_second": 3.184,
70
+ "eval_wer": 1.0,
71
+ "eval_wer_clean": 1.0,
72
+ "step": 1200
73
+ },
74
+ {
75
+ "epoch": 1.6,
76
+ "learning_rate": 8.994e-06,
77
+ "loss": 3.3754,
78
+ "step": 1500
79
+ },
80
+ {
81
+ "epoch": 1.6,
82
+ "eval_loss": 3.3332014083862305,
83
+ "eval_runtime": 150.7828,
84
+ "eval_samples_per_second": 25.348,
85
+ "eval_steps_per_second": 3.17,
86
+ "eval_wer": 1.0,
87
+ "eval_wer_clean": 1.0,
88
+ "step": 1500
89
+ },
90
+ {
91
+ "epoch": 1.92,
92
+ "learning_rate": 1.0794e-05,
93
+ "loss": 3.3223,
94
+ "step": 1800
95
+ },
96
+ {
97
+ "epoch": 1.92,
98
+ "eval_loss": 3.281956195831299,
99
+ "eval_runtime": 152.0654,
100
+ "eval_samples_per_second": 25.134,
101
+ "eval_steps_per_second": 3.143,
102
+ "eval_wer": 1.0,
103
+ "eval_wer_clean": 1.0,
104
+ "step": 1800
105
+ },
106
+ {
107
+ "epoch": 2.24,
108
+ "learning_rate": 1.2594e-05,
109
+ "loss": 3.2219,
110
+ "step": 2100
111
+ },
112
+ {
113
+ "epoch": 2.24,
114
+ "eval_loss": 2.974060297012329,
115
+ "eval_runtime": 150.2485,
116
+ "eval_samples_per_second": 25.438,
117
+ "eval_steps_per_second": 3.181,
118
+ "eval_wer": 1.0,
119
+ "eval_wer_clean": 1.0,
120
+ "step": 2100
121
+ },
122
+ {
123
+ "epoch": 2.56,
124
+ "learning_rate": 1.4394e-05,
125
+ "loss": 2.8883,
126
+ "step": 2400
127
+ },
128
+ {
129
+ "epoch": 2.56,
130
+ "eval_loss": 2.3728537559509277,
131
+ "eval_runtime": 150.7057,
132
+ "eval_samples_per_second": 25.361,
133
+ "eval_steps_per_second": 3.172,
134
+ "eval_wer": 0.9934450109249818,
135
+ "eval_wer_clean": 0.9934450109249818,
136
+ "step": 2400
137
+ },
138
+ {
139
+ "epoch": 2.88,
140
+ "learning_rate": 1.6193999999999998e-05,
141
+ "loss": 2.4547,
142
+ "step": 2700
143
+ },
144
+ {
145
+ "epoch": 2.88,
146
+ "eval_loss": 1.8045622110366821,
147
+ "eval_runtime": 152.533,
148
+ "eval_samples_per_second": 25.057,
149
+ "eval_steps_per_second": 3.134,
150
+ "eval_wer": 0.9780746917145943,
151
+ "eval_wer_clean": 0.9780746917145943,
152
+ "step": 2700
153
+ }
154
+ ],
155
+ "max_steps": 3000,
156
+ "num_train_epochs": 4,
157
+ "total_flos": 8.463814494773632e+18,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee9fb11de410484a4725600f651ae616ce637b063b29c76199317daae22692f5
3
+ size 3963