Hugging Face's logo

ylacombe
/
wav2vec2-bert-CV16-en-cv-2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
wav2vec2-bert
mozilla-foundation/common_voice_16_0
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ylacombe HF staff commited on
Commit
64ca739
•
1 Parent(s): f4b0b3a

Model save

Browse files
Files changed (4) hide show
  1. README.md +169 -0
  2. emissions.csv +2 -0
  3. model.safetensors +1 -1
  4. runs/Jan18_18-29-35_vorace/events.out.tfevents.1705602788.vorace.881300.0 +2 -2
README.md ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: facebook/w2v-bert-2.0
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-bert-CV16-en-cv-2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # wav2vec2-bert-CV16-en-cv-2
17
+
18
+ This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4371
21
+ - Wer: 0.1304
22
+ - Cer: 0.0528
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 12
43
+ - eval_batch_size: 12
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - num_devices: 3
47
+ - gradient_accumulation_steps: 3
48
+ - total_train_batch_size: 108
49
+ - total_eval_batch_size: 36
50
+ - optimizer: Adam with betas=(0.9,0.96) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 10000
53
+ - num_epochs: 50.0
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-----:|:------:|:---------------:|:------:|:------:|
60
+ | 0.1884 | 0.49 | 5000 | 0.3214 | 0.1872 | 0.0699 |
61
+ | 0.1862 | 0.98 | 10000 | 0.2829 | 0.1759 | 0.0674 |
62
+ | 0.1493 | 1.47 | 15000 | 0.2955 | 0.1680 | 0.0658 |
63
+ | 0.1346 | 1.96 | 20000 | 0.2727 | 0.1649 | 0.0647 |
64
+ | 0.1273 | 2.45 | 25000 | 0.2677 | 0.1608 | 0.0631 |
65
+ | 0.1241 | 2.94 | 30000 | 0.2613 | 0.1594 | 0.0631 |
66
+ | 0.1059 | 3.43 | 35000 | 0.2737 | 0.1600 | 0.0636 |
67
+ | 0.1201 | 3.92 | 40000 | 0.2633 | 0.1553 | 0.0618 |
68
+ | 0.0961 | 4.4 | 45000 | 0.2666 | 0.1549 | 0.0617 |
69
+ | 0.0971 | 4.89 | 50000 | 0.2647 | 0.1536 | 0.0616 |
70
+ | 0.088 | 5.38 | 55000 | 0.2504 | 0.1500 | 0.0597 |
71
+ | 0.0931 | 5.87 | 60000 | 0.2494 | 0.1500 | 0.0599 |
72
+ | 0.0906 | 6.36 | 65000 | 0.2604 | 0.1507 | 0.0602 |
73
+ | 0.0788 | 6.85 | 70000 | 0.2629 | 0.1506 | 0.0603 |
74
+ | 0.0692 | 7.34 | 75000 | 0.2500 | 0.1484 | 0.0590 |
75
+ | 0.0896 | 7.83 | 80000 | 0.2525 | 0.1468 | 0.0586 |
76
+ | 0.0794 | 8.32 | 85000 | 0.2494 | 0.1458 | 0.0583 |
77
+ | 0.0908 | 8.81 | 90000 | 0.2539 | 0.1475 | 0.0587 |
78
+ | 0.0646 | 9.3 | 95000 | 0.2539 | 0.1457 | 0.0578 |
79
+ | 0.0877 | 9.79 | 100000 | 0.2503 | 0.1453 | 0.0583 |
80
+ | 0.0657 | 10.28 | 105000 | 0.2589 | 0.1457 | 0.0586 |
81
+ | 0.0715 | 10.77 | 110000 | 0.2638 | 0.1462 | 0.0586 |
82
+ | 0.0704 | 11.26 | 115000 | 0.2562 | 0.1419 | 0.0571 |
83
+ | 0.0582 | 11.75 | 120000 | 0.2663 | 0.1425 | 0.0577 |
84
+ | 0.0583 | 12.23 | 125000 | 0.2615 | 0.1408 | 0.0573 |
85
+ | 0.0776 | 12.72 | 130000 | 0.2593 | 0.1434 | 0.0575 |
86
+ | 0.0624 | 13.21 | 135000 | 0.2603 | 0.1438 | 0.0577 |
87
+ | 0.0619 | 13.7 | 140000 | 0.2512 | 0.1391 | 0.0564 |
88
+ | 0.0642 | 14.19 | 145000 | 0.2539 | 0.1386 | 0.0558 |
89
+ | 0.0593 | 14.68 | 150000 | 0.2609 | 0.1406 | 0.0567 |
90
+ | 0.0596 | 15.17 | 155000 | 0.2567 | 0.1390 | 0.0562 |
91
+ | 0.0671 | 15.66 | 160000 | 0.2618 | 0.1404 | 0.0574 |
92
+ | 0.0537 | 16.15 | 165000 | 0.2668 | 0.1391 | 0.0565 |
93
+ | 0.0543 | 16.64 | 170000 | 0.2583 | 0.1379 | 0.0560 |
94
+ | 0.056 | 17.13 | 175000 | 0.2612 | 0.1395 | 0.0564 |
95
+ | 0.0605 | 17.62 | 180000 | 0.2654 | 0.1375 | 0.0557 |
96
+ | 0.0536 | 18.11 | 185000 | 0.2703 | 0.1356 | 0.0549 |
97
+ | 0.0469 | 18.6 | 190000 | 0.2571 | 0.1348 | 0.0548 |
98
+ | 0.0548 | 19.09 | 195000 | 0.2621 | 0.1359 | 0.0551 |
99
+ | 0.0507 | 19.58 | 200000 | 0.2628 | 0.1348 | 0.0549 |
100
+ | 0.0513 | 20.06 | 205000 | 0.2722 | 0.1367 | 0.0558 |
101
+ | 0.0423 | 20.55 | 210000 | 0.2752 | 0.1349 | 0.0546 |
102
+ | 0.049 | 21.04 | 215000 | 0.2777 | 0.1358 | 0.0552 |
103
+ | 0.0434 | 21.53 | 220000 | 0.2671 | 0.1336 | 0.0549 |
104
+ | 0.0443 | 22.02 | 225000 | 0.2815 | 0.1333 | 0.0544 |
105
+ | 0.0533 | 22.51 | 230000 | 0.2674 | 0.1334 | 0.0542 |
106
+ | 0.0458 | 23.0 | 235000 | 0.2746 | 0.1320 | 0.0541 |
107
+ | 0.0527 | 23.49 | 240000 | 0.2750 | 0.1351 | 0.0546 |
108
+ | 0.0458 | 23.98 | 245000 | 0.2748 | 0.1322 | 0.0539 |
109
+ | 0.0434 | 24.47 | 250000 | 0.2774 | 0.1317 | 0.0538 |
110
+ | 0.0434 | 24.96 | 255000 | 0.2756 | 0.1322 | 0.0534 |
111
+ | 0.041 | 25.45 | 260000 | 0.2786 | 0.1337 | 0.0542 |
112
+ | 0.0408 | 25.94 | 265000 | 0.2785 | 0.1320 | 0.0534 |
113
+ | 0.0486 | 26.43 | 270000 | 0.2882 | 0.1325 | 0.0536 |
114
+ | 0.0469 | 26.92 | 275000 | 0.2796 | 0.1315 | 0.0532 |
115
+ | 0.041 | 27.41 | 280000 | 0.2786 | 0.1319 | 0.0536 |
116
+ | 0.0333 | 27.89 | 285000 | 0.2893 | 0.1316 | 0.0532 |
117
+ | 0.0391 | 28.38 | 290000 | 0.2893 | 0.1318 | 0.0537 |
118
+ | 0.0427 | 28.87 | 295000 | 0.3006 | 0.1326 | 0.0535 |
119
+ | 0.0469 | 29.36 | 300000 | 0.2846 | 0.1308 | 0.0530 |
120
+ | 0.0317 | 29.85 | 305000 | 0.3140 | 0.1311 | 0.0534 |
121
+ | 0.0373 | 30.34 | 310000 | 0.2951 | 0.1314 | 0.0533 |
122
+ | 0.0367 | 30.83 | 315000 | 0.2976 | 0.1309 | 0.0532 |
123
+ | 0.0385 | 31.32 | 320000 | 0.3068 | 0.1311 | 0.0534 |
124
+ | 0.0372 | 31.81 | 325000 | 0.3085 | 0.1295 | 0.0527 |
125
+ | 0.0342 | 32.3 | 330000 | 0.3150 | 0.1290 | 0.0527 |
126
+ | 0.035 | 32.79 | 335000 | 0.3133 | 0.1299 | 0.0530 |
127
+ | 0.0331 | 33.28 | 340000 | 0.3201 | 0.1303 | 0.0530 |
128
+ | 0.0334 | 33.77 | 345000 | 0.3310 | 0.1294 | 0.0527 |
129
+ | 0.0353 | 34.26 | 350000 | 0.3105 | 0.1287 | 0.0523 |
130
+ | 0.0367 | 34.75 | 355000 | 0.3180 | 0.1302 | 0.0530 |
131
+ | 0.0397 | 35.24 | 360000 | 0.3322 | 0.1297 | 0.0528 |
132
+ | 0.0384 | 35.72 | 365000 | 0.3290 | 0.1303 | 0.0530 |
133
+ | 0.0349 | 36.21 | 370000 | 0.3358 | 0.1298 | 0.0529 |
134
+ | 0.0352 | 36.7 | 375000 | 0.3351 | 0.1347 | 0.0546 |
135
+ | 0.0333 | 37.19 | 380000 | 0.3420 | 0.1296 | 0.0528 |
136
+ | 0.0282 | 37.68 | 385000 | 0.3426 | 0.1317 | 0.0534 |
137
+ | 0.0247 | 38.17 | 390000 | 0.3606 | 0.1318 | 0.0531 |
138
+ | 0.0312 | 38.66 | 395000 | 0.3509 | 0.1494 | 0.0601 |
139
+ | 0.0288 | 39.15 | 400000 | 0.3516 | 0.1325 | 0.0536 |
140
+ | 0.0281 | 39.64 | 405000 | 0.3489 | 0.1303 | 0.0528 |
141
+ | 0.0208 | 40.13 | 410000 | 0.3661 | 0.1430 | 0.0576 |
142
+ | 0.0276 | 40.62 | 415000 | 0.3620 | 0.1300 | 0.0524 |
143
+ | 0.0253 | 41.11 | 420000 | 0.3786 | 0.1328 | 0.0538 |
144
+ | 0.025 | 41.6 | 425000 | 0.3782 | 0.1321 | 0.0535 |
145
+ | 0.02 | 42.09 | 430000 | 0.3721 | 0.1297 | 0.0523 |
146
+ | 0.0192 | 42.58 | 435000 | 0.4099 | 0.1308 | 0.0528 |
147
+ | 0.0197 | 43.07 | 440000 | 0.3970 | 0.1292 | 0.0525 |
148
+ | 0.0177 | 43.55 | 445000 | 0.3946 | 0.1306 | 0.0531 |
149
+ | 0.0185 | 44.04 | 450000 | 0.4060 | 0.1293 | 0.0526 |
150
+ | 0.0176 | 44.53 | 455000 | 0.3968 | 0.1303 | 0.0529 |
151
+ | 0.0126 | 45.02 | 460000 | 0.3994 | 0.1304 | 0.0529 |
152
+ | 0.0142 | 45.51 | 465000 | 0.3975 | 0.1300 | 0.0527 |
153
+ | 0.0122 | 46.0 | 470000 | 0.4055 | 0.1287 | 0.0523 |
154
+ | 0.0115 | 46.49 | 475000 | 0.4211 | 0.1303 | 0.0526 |
155
+ | 0.0102 | 46.98 | 480000 | 0.4148 | 0.1298 | 0.0525 |
156
+ | 0.0119 | 47.47 | 485000 | 0.4238 | 0.1301 | 0.0527 |
157
+ | 0.0098 | 47.96 | 490000 | 0.4293 | 0.1299 | 0.0526 |
158
+ | 0.0125 | 48.45 | 495000 | 0.4375 | 0.1300 | 0.0526 |
159
+ | 0.0095 | 48.94 | 500000 | 0.4268 | 0.1303 | 0.0527 |
160
+ | 0.0055 | 49.43 | 505000 | 0.4286 | 0.1305 | 0.0527 |
161
+ | 0.0089 | 49.92 | 510000 | 0.4371 | 0.1304 | 0.0528 |
162
+
163
+
164
+ ### Framework versions
165
+
166
+ - Transformers 4.37.0.dev0
167
+ - Pytorch 2.1.0+cu121
168
+ - Datasets 2.16.1
169
+ - Tokenizers 0.15.0
emissions.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
2
+ 2024-02-01T10:19:31,691dd5c4-fb0e-4ae1-a396-03660afcd381,codecarbon,1179980.7668220997,111.24542012565495,262.01043532587414,France,FRA,île-de-france,N,,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:165c602b1419d5e30e30de67f0dce9e0ef8e846ec1a15f4a75900cdf05354610
3
  size 2422949860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45a264c27487b58812e802b6f52eb529a8147685f610c9867c5c87b52301e329
3
  size 2422949860
runs/Jan18_18-29-35_vorace/events.out.tfevents.1705602788.vorace.881300.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d59f1d48f9da50e7f241cf26533c225849e90f6d4abdba9b0ca3533fc64618f
3
- size 16353657
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700eadd51a8f30872933a09bdb20db70050593537428128ac17b9403e0a99b75
3
+ size 16381217