Hugging Face's logo

spktsagar
/
wav2vec2-large-xls-r-300m-nepali-openslr

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Nepali
wav2vec2
Generated from Trainer
speech
openslr
nepali
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
spktsagar commited on
Commit
36d6843
•
1 Parent(s): 892b0a1

Training in progress, step 10400

Browse files
Files changed (12) hide show
  1. last-checkpoint/config.json +108 -0
  2. last-checkpoint/optimizer.pt +3 -0
  3. last-checkpoint/preprocessor_config.json +10 -0
  4. last-checkpoint/pytorch_model.bin +3 -0
  5. last-checkpoint/rng_state.pth +3 -0
  6. last-checkpoint/scaler.pt +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/trainer_state.json +211 -0
  9. last-checkpoint/training_args.bin +3 -0
  10. pytorch_model.bin +1 -1
  11. runs/Oct23_02-58-56_b807f884dd1e/1666504762.0300505/events.out.tfevents.1666504762.b807f884dd1e.75.2 +3 -0
  12. runs/Oct23_02-58-56_b807f884dd1e/events.out.tfevents.1666494605.b807f884dd1e.75.0 +2 -2
last-checkpoint/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
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": 0.1,
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
+ "gradient_checkpointing": false,
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_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.075,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 24,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1024,
80
+ "pad_token_id": 0,
81
+ "proj_codevector_dim": 768,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.23.1",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 81,
107
+ "xvector_output_dim": 512
108
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f202ac1febc41e3ea4dec5365eee10c623d81815caa3c52d919717f8185049
3
+ size 2490723217
last-checkpoint/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
+ }
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5f1a6062373a138361c123e818fed6c261f3c1d63e907df5f5a83e954d67b6
3
+ size 1262230833
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa39a089138449bbf5257163299788bafdd39b539dc740883ee39e19ebefc8d2
3
+ size 14567
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2833dd960361d4aa43002cc253d8c2874180b465655a351aaf7f30e71933a722
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f852313013dcf68629d7d1272b9e6823ca03c1433cfa0fb60f50bc88a07b040
3
+ size 623
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.7195711857759184,
5
+ "global_step": 10400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.21,
12
+ "learning_rate": 0.0002976391096979332,
13
+ "loss": 6.4525,
14
+ "step": 800
15
+ },
16
+ {
17
+ "epoch": 0.21,
18
+ "eval_loss": 1.4264159202575684,
19
+ "eval_runtime": 579.6055,
20
+ "eval_samples_per_second": 37.262,
21
+ "eval_steps_per_second": 4.658,
22
+ "eval_wer": 0.9522086267891338,
23
+ "step": 800
24
+ },
25
+ {
26
+ "epoch": 0.42,
27
+ "learning_rate": 0.00029127980922098566,
28
+ "loss": 1.105,
29
+ "step": 1600
30
+ },
31
+ {
32
+ "epoch": 0.42,
33
+ "eval_loss": 0.5966897010803223,
34
+ "eval_runtime": 638.739,
35
+ "eval_samples_per_second": 33.812,
36
+ "eval_steps_per_second": 4.227,
37
+ "eval_wer": 0.6514394209860115,
38
+ "step": 1600
39
+ },
40
+ {
41
+ "epoch": 0.63,
42
+ "learning_rate": 0.00028492050874403814,
43
+ "loss": 0.7933,
44
+ "step": 2400
45
+ },
46
+ {
47
+ "epoch": 0.63,
48
+ "eval_loss": 0.44666677713394165,
49
+ "eval_runtime": 578.27,
50
+ "eval_samples_per_second": 37.348,
51
+ "eval_steps_per_second": 4.669,
52
+ "eval_wer": 0.5045276037778715,
53
+ "step": 2400
54
+ },
55
+ {
56
+ "epoch": 0.84,
57
+ "learning_rate": 0.00027856120826709056,
58
+ "loss": 0.6926,
59
+ "step": 3200
60
+ },
61
+ {
62
+ "epoch": 0.84,
63
+ "eval_loss": 0.3889370858669281,
64
+ "eval_runtime": 574.1787,
65
+ "eval_samples_per_second": 37.614,
66
+ "eval_steps_per_second": 4.702,
67
+ "eval_wer": 0.4508941611762033,
68
+ "step": 3200
69
+ },
70
+ {
71
+ "epoch": 1.05,
72
+ "learning_rate": 0.0002722019077901431,
73
+ "loss": 0.6258,
74
+ "step": 4000
75
+ },
76
+ {
77
+ "epoch": 1.05,
78
+ "eval_loss": 0.33456486463546753,
79
+ "eval_runtime": 575.0581,
80
+ "eval_samples_per_second": 37.556,
81
+ "eval_steps_per_second": 4.695,
82
+ "eval_wer": 0.39778001363149523,
83
+ "step": 4000
84
+ },
85
+ {
86
+ "epoch": 1.26,
87
+ "learning_rate": 0.0002658426073131955,
88
+ "loss": 0.5666,
89
+ "step": 4800
90
+ },
91
+ {
92
+ "epoch": 1.26,
93
+ "eval_loss": 0.31256240606307983,
94
+ "eval_runtime": 592.8115,
95
+ "eval_samples_per_second": 36.431,
96
+ "eval_steps_per_second": 4.555,
97
+ "eval_wer": 0.3761481289149979,
98
+ "step": 4800
99
+ },
100
+ {
101
+ "epoch": 1.46,
102
+ "learning_rate": 0.000259483306836248,
103
+ "loss": 0.5501,
104
+ "step": 5600
105
+ },
106
+ {
107
+ "epoch": 1.46,
108
+ "eval_loss": 0.2980588376522064,
109
+ "eval_runtime": 662.1285,
110
+ "eval_samples_per_second": 32.618,
111
+ "eval_steps_per_second": 4.078,
112
+ "eval_wer": 0.3593684073869722,
113
+ "step": 5600
114
+ },
115
+ {
116
+ "epoch": 1.67,
117
+ "learning_rate": 0.00025313195548489663,
118
+ "loss": 0.5275,
119
+ "step": 6400
120
+ },
121
+ {
122
+ "epoch": 1.67,
123
+ "eval_loss": 0.28137603402137756,
124
+ "eval_runtime": 588.9138,
125
+ "eval_samples_per_second": 36.673,
126
+ "eval_steps_per_second": 4.585,
127
+ "eval_wer": 0.3457206841712375,
128
+ "step": 6400
129
+ },
130
+ {
131
+ "epoch": 1.88,
132
+ "learning_rate": 0.0002467726550079491,
133
+ "loss": 0.5203,
134
+ "step": 7200
135
+ },
136
+ {
137
+ "epoch": 1.88,
138
+ "eval_loss": 0.2654956877231598,
139
+ "eval_runtime": 586.4688,
140
+ "eval_samples_per_second": 36.825,
141
+ "eval_steps_per_second": 4.604,
142
+ "eval_wer": 0.3303041121677323,
143
+ "step": 7200
144
+ },
145
+ {
146
+ "epoch": 2.09,
147
+ "learning_rate": 0.00024041335453100157,
148
+ "loss": 0.4842,
149
+ "step": 8000
150
+ },
151
+ {
152
+ "epoch": 2.09,
153
+ "eval_loss": 0.2574324607849121,
154
+ "eval_runtime": 641.5915,
155
+ "eval_samples_per_second": 33.662,
156
+ "eval_steps_per_second": 4.208,
157
+ "eval_wer": 0.31566648274966735,
158
+ "step": 8000
159
+ },
160
+ {
161
+ "epoch": 2.3,
162
+ "learning_rate": 0.00023405405405405404,
163
+ "loss": 0.4542,
164
+ "step": 8800
165
+ },
166
+ {
167
+ "epoch": 2.3,
168
+ "eval_loss": 0.2577317953109741,
169
+ "eval_runtime": 583.455,
170
+ "eval_samples_per_second": 37.016,
171
+ "eval_steps_per_second": 4.628,
172
+ "eval_wer": 0.31417350946090683,
173
+ "step": 8800
174
+ },
175
+ {
176
+ "epoch": 2.51,
177
+ "learning_rate": 0.0002276947535771065,
178
+ "loss": 0.4431,
179
+ "step": 9600
180
+ },
181
+ {
182
+ "epoch": 2.51,
183
+ "eval_loss": 0.23904646933078766,
184
+ "eval_runtime": 581.9022,
185
+ "eval_samples_per_second": 37.114,
186
+ "eval_steps_per_second": 4.64,
187
+ "eval_wer": 0.2938236344162799,
188
+ "step": 9600
189
+ },
190
+ {
191
+ "epoch": 2.72,
192
+ "learning_rate": 0.00022133545310015898,
193
+ "loss": 0.4235,
194
+ "step": 10400
195
+ },
196
+ {
197
+ "epoch": 2.72,
198
+ "eval_loss": 0.24016053974628448,
199
+ "eval_runtime": 582.7306,
200
+ "eval_samples_per_second": 37.062,
201
+ "eval_steps_per_second": 4.633,
202
+ "eval_wer": 0.2884684041413781,
203
+ "step": 10400
204
+ }
205
+ ],
206
+ "max_steps": 38240,
207
+ "num_train_epochs": 10,
208
+ "total_flos": 3.3068721437568434e+19,
209
+ "trial_name": null,
210
+ "trial_params": null
211
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f010247e36de93b78cc4e817f21fbc3e16af65633f28b4e8e47d3aa11d0a94
3
+ size 3439
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ad718969b64529c72f939550444d04e3c18581c0201068054dcf72cb294061e
3
  size 1262230833
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5f1a6062373a138361c123e818fed6c261f3c1d63e907df5f5a83e954d67b6
3
  size 1262230833
runs/Oct23_02-58-56_b807f884dd1e/1666504762.0300505/events.out.tfevents.1666504762.b807f884dd1e.75.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7269b4978e31abe1febcd3df6d38b026f30b8e5d7b4aa62add73c4084df33a4
3
+ size 5570
runs/Oct23_02-58-56_b807f884dd1e/events.out.tfevents.1666494605.b807f884dd1e.75.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4269e374992dd1d65933223cf7dd27670ac315a2323b2f1d4e44f32bfad70ef9
3
- size 7124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265f585e4800d703310c493720087e94179f5842902aa4248d5c0bb15cfb2174
3
+ size 12775