Hugging Face's logo

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

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
07ca45d
•
1 Parent(s): 9640f85

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/Jan16_16-58-34_vorace/events.out.tfevents.1705426135.vorace.518965.0 +2 -2
README.md ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: ylacombe/wav2vec2-bert-CV16-en-libri
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-bert-CV16-en-libri-cv
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-libri-cv
17
+
18
+ This model is a fine-tuned version of [ylacombe/wav2vec2-bert-CV16-en-libri](https://huggingface.co/ylacombe/wav2vec2-bert-CV16-en-libri) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2169
21
+ - Wer: 0.1351
22
+ - Cer: 0.0524
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=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 15000
53
+ - num_epochs: 5.0
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.3302 | 0.05 | 500 | 0.4543 | 0.2333 | 0.0889 |
61
+ | 0.2579 | 0.1 | 1000 | 0.4172 | 0.2213 | 0.0832 |
62
+ | 0.2527 | 0.15 | 1500 | 0.3999 | 0.2142 | 0.0799 |
63
+ | 0.269 | 0.2 | 2000 | 0.3763 | 0.2049 | 0.0768 |
64
+ | 0.229 | 0.24 | 2500 | 0.3629 | 0.2029 | 0.0753 |
65
+ | 0.2286 | 0.29 | 3000 | 0.3494 | 0.1972 | 0.0733 |
66
+ | 0.2422 | 0.34 | 3500 | 0.3365 | 0.1929 | 0.0720 |
67
+ | 0.1989 | 0.39 | 4000 | 0.3362 | 0.1900 | 0.0711 |
68
+ | 0.2036 | 0.44 | 4500 | 0.3282 | 0.1871 | 0.0696 |
69
+ | 0.198 | 0.49 | 5000 | 0.3156 | 0.1803 | 0.0677 |
70
+ | 0.1757 | 0.54 | 5500 | 0.3069 | 0.1797 | 0.0682 |
71
+ | 0.1966 | 0.59 | 6000 | 0.2984 | 0.1786 | 0.0663 |
72
+ | 0.1924 | 0.64 | 6500 | 0.3014 | 0.1795 | 0.0676 |
73
+ | 0.19 | 0.68 | 7000 | 0.3059 | 0.1741 | 0.0656 |
74
+ | 0.1723 | 0.73 | 7500 | 0.3036 | 0.1758 | 0.0673 |
75
+ | 0.1688 | 0.78 | 8000 | 0.2990 | 0.1749 | 0.0670 |
76
+ | 0.1776 | 0.83 | 8500 | 0.2984 | 0.1742 | 0.0663 |
77
+ | 0.151 | 0.88 | 9000 | 0.3027 | 0.1707 | 0.0651 |
78
+ | 0.1609 | 0.93 | 9500 | 0.3001 | 0.1738 | 0.0667 |
79
+ | 0.1735 | 0.98 | 10000 | 0.3007 | 0.1748 | 0.0667 |
80
+ | 0.1355 | 1.03 | 10500 | 0.2953 | 0.1716 | 0.0665 |
81
+ | 0.1538 | 1.08 | 11000 | 0.2872 | 0.1733 | 0.0672 |
82
+ | 0.1448 | 1.12 | 11500 | 0.2927 | 0.1695 | 0.0657 |
83
+ | 0.1686 | 1.17 | 12000 | 0.2864 | 0.1731 | 0.0673 |
84
+ | 0.1506 | 1.22 | 12500 | 0.2891 | 0.1734 | 0.0667 |
85
+ | 0.1621 | 1.27 | 13000 | 0.2837 | 0.1722 | 0.0669 |
86
+ | 0.1573 | 1.32 | 13500 | 0.2792 | 0.1728 | 0.0660 |
87
+ | 0.1566 | 1.37 | 14000 | 0.2747 | 0.1702 | 0.0661 |
88
+ | 0.1528 | 1.42 | 14500 | 0.2781 | 0.1754 | 0.0673 |
89
+ | 0.153 | 1.47 | 15000 | 0.2900 | 0.1788 | 0.0692 |
90
+ | 0.1575 | 1.52 | 15500 | 0.2713 | 0.1758 | 0.0670 |
91
+ | 0.1543 | 1.56 | 16000 | 0.2846 | 0.1728 | 0.0666 |
92
+ | 0.1354 | 1.61 | 16500 | 0.2781 | 0.1696 | 0.0657 |
93
+ | 0.1246 | 1.66 | 17000 | 0.2941 | 0.1729 | 0.0674 |
94
+ | 0.1538 | 1.71 | 17500 | 0.2803 | 0.1707 | 0.0662 |
95
+ | 0.143 | 1.76 | 18000 | 0.2705 | 0.1669 | 0.0650 |
96
+ | 0.1505 | 1.81 | 18500 | 0.2632 | 0.1687 | 0.0653 |
97
+ | 0.1415 | 1.86 | 19000 | 0.2623 | 0.1651 | 0.0636 |
98
+ | 0.1402 | 1.91 | 19500 | 0.2607 | 0.1668 | 0.0647 |
99
+ | 0.1354 | 1.96 | 20000 | 0.2649 | 0.1643 | 0.0635 |
100
+ | 0.1234 | 2.0 | 20500 | 0.2684 | 0.1616 | 0.0636 |
101
+ | 0.129 | 2.05 | 21000 | 0.2589 | 0.1595 | 0.0624 |
102
+ | 0.1198 | 2.1 | 21500 | 0.2629 | 0.1629 | 0.0631 |
103
+ | 0.1083 | 2.15 | 22000 | 0.2608 | 0.1604 | 0.0627 |
104
+ | 0.1446 | 2.2 | 22500 | 0.2598 | 0.1614 | 0.0629 |
105
+ | 0.1315 | 2.25 | 23000 | 0.2681 | 0.1640 | 0.0643 |
106
+ | 0.1218 | 2.3 | 23500 | 0.2616 | 0.1607 | 0.0639 |
107
+ | 0.1167 | 2.35 | 24000 | 0.2732 | 0.1599 | 0.0627 |
108
+ | 0.1009 | 2.4 | 24500 | 0.2566 | 0.1600 | 0.0627 |
109
+ | 0.1133 | 2.44 | 25000 | 0.2533 | 0.1566 | 0.0614 |
110
+ | 0.1135 | 2.49 | 25500 | 0.2470 | 0.1561 | 0.0606 |
111
+ | 0.1042 | 2.54 | 26000 | 0.2508 | 0.1546 | 0.0604 |
112
+ | 0.1238 | 2.59 | 26500 | 0.2568 | 0.1565 | 0.0616 |
113
+ | 0.1178 | 2.64 | 27000 | 0.2564 | 0.1574 | 0.0615 |
114
+ | 0.1207 | 2.69 | 27500 | 0.2456 | 0.1552 | 0.0605 |
115
+ | 0.1112 | 2.74 | 28000 | 0.2434 | 0.1516 | 0.0595 |
116
+ | 0.1097 | 2.79 | 28500 | 0.2467 | 0.1550 | 0.0605 |
117
+ | 0.1253 | 2.84 | 29000 | 0.2428 | 0.1541 | 0.0600 |
118
+ | 0.1172 | 2.88 | 29500 | 0.2399 | 0.1513 | 0.0592 |
119
+ | 0.12 | 2.93 | 30000 | 0.2393 | 0.1518 | 0.0589 |
120
+ | 0.0976 | 2.98 | 30500 | 0.2442 | 0.1520 | 0.0596 |
121
+ | 0.1422 | 3.03 | 31000 | 0.2398 | 0.1503 | 0.0588 |
122
+ | 0.1285 | 3.08 | 31500 | 0.2446 | 0.1518 | 0.0591 |
123
+ | 0.122 | 3.13 | 32000 | 0.2401 | 0.1503 | 0.0587 |
124
+ | 0.1132 | 3.18 | 32500 | 0.2437 | 0.1514 | 0.0591 |
125
+ | 0.1275 | 3.23 | 33000 | 0.2466 | 0.1485 | 0.0584 |
126
+ | 0.1299 | 3.28 | 33500 | 0.2380 | 0.1463 | 0.0571 |
127
+ | 0.1129 | 3.32 | 34000 | 0.2416 | 0.1472 | 0.0576 |
128
+ | 0.1367 | 3.37 | 34500 | 0.2418 | 0.1479 | 0.0581 |
129
+ | 0.1166 | 3.42 | 35000 | 0.2418 | 0.1458 | 0.0573 |
130
+ | 0.1264 | 3.47 | 35500 | 0.2349 | 0.1449 | 0.0569 |
131
+ | 0.1325 | 3.52 | 36000 | 0.2332 | 0.1458 | 0.0567 |
132
+ | 0.1208 | 3.57 | 36500 | 0.2372 | 0.1469 | 0.0578 |
133
+ | 0.1309 | 3.62 | 37000 | 0.2354 | 0.1455 | 0.0570 |
134
+ | 0.1303 | 3.67 | 37500 | 0.2281 | 0.1435 | 0.0559 |
135
+ | 0.1193 | 3.72 | 38000 | 0.2306 | 0.1438 | 0.0563 |
136
+ | 0.1148 | 3.76 | 38500 | 0.2259 | 0.1439 | 0.0558 |
137
+ | 0.1066 | 3.81 | 39000 | 0.2293 | 0.1421 | 0.0558 |
138
+ | 0.0899 | 3.86 | 39500 | 0.2266 | 0.1408 | 0.0552 |
139
+ | 0.123 | 3.91 | 40000 | 0.2254 | 0.1419 | 0.0555 |
140
+ | 0.1162 | 3.96 | 40500 | 0.2251 | 0.1422 | 0.0557 |
141
+ | 0.0856 | 4.01 | 41000 | 0.2253 | 0.1401 | 0.0549 |
142
+ | 0.0983 | 4.06 | 41500 | 0.2258 | 0.1389 | 0.0547 |
143
+ | 0.0893 | 4.11 | 42000 | 0.2260 | 0.1406 | 0.0547 |
144
+ | 0.0892 | 4.16 | 42500 | 0.2272 | 0.1391 | 0.0544 |
145
+ | 0.0761 | 4.2 | 43000 | 0.2301 | 0.1396 | 0.0547 |
146
+ | 0.0931 | 4.25 | 43500 | 0.2259 | 0.1377 | 0.0538 |
147
+ | 0.081 | 4.3 | 44000 | 0.2221 | 0.1389 | 0.0540 |
148
+ | 0.0878 | 4.35 | 44500 | 0.2232 | 0.1383 | 0.0538 |
149
+ | 0.0837 | 4.4 | 45000 | 0.2258 | 0.1381 | 0.0540 |
150
+ | 0.0917 | 4.45 | 45500 | 0.2211 | 0.1371 | 0.0535 |
151
+ | 0.0736 | 4.5 | 46000 | 0.2226 | 0.1364 | 0.0534 |
152
+ | 0.0728 | 4.55 | 46500 | 0.2218 | 0.1358 | 0.0531 |
153
+ | 0.0824 | 4.6 | 47000 | 0.2205 | 0.1365 | 0.0533 |
154
+ | 0.0794 | 4.64 | 47500 | 0.2198 | 0.1359 | 0.0529 |
155
+ | 0.0823 | 4.69 | 48000 | 0.2199 | 0.1354 | 0.0527 |
156
+ | 0.0849 | 4.74 | 48500 | 0.2176 | 0.1348 | 0.0525 |
157
+ | 0.095 | 4.79 | 49000 | 0.2185 | 0.1354 | 0.0529 |
158
+ | 0.0951 | 4.84 | 49500 | 0.2163 | 0.1354 | 0.0527 |
159
+ | 0.0902 | 4.89 | 50000 | 0.2163 | 0.1350 | 0.0525 |
160
+ | 0.066 | 4.94 | 50500 | 0.2167 | 0.1350 | 0.0525 |
161
+ | 0.0776 | 4.99 | 51000 | 0.2169 | 0.1351 | 0.0524 |
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
+ 2024-01-18T18:07:06,c448b4d8-753d-421b-9a0f-ac213e62eca4,codecarbon,175088.33953380585,13.792693683515147,32.48519959070955,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:d4130bf0a1031a5c86ce42bb3490d5a23933effe8f1319af3fbafcd7b568c6bb
3
  size 2422949860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606855e70e2d645a47b66199a7f249b6108bbaaace935a7f74e4f0b91d9f12a7
3
  size 2422949860
runs/Jan16_16-58-34_vorace/events.out.tfevents.1705426135.vorace.518965.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6289a1d1d64166aafc9d695894c6e83959865e2bc60971e15663eeeb2368082c
3
- size 1665481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91c15dcaa7d4730142d97477f5f65b34922449c38f39da0f5c97e2f32c6dfa4
3
+ size 1670001