Hugging Face's logo

St4n
/
wav2vec2-base-timit-demo-google-colab

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
St4n commited on
Commit
9c34342
•
1 Parent(s): 8584d11

End of training

Browse files
Files changed (3) hide show
  1. README.md +50 -9
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
3
  base_model: facebook/wav2vec2-base-100h
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: wav2vec2-base-timit-demo-google-colab
8
  results: []
@@ -15,13 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/wav2vec2-base-100h](https://huggingface.co/facebook/wav2vec2-base-100h) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.1662
19
- - eval_wer: 0.1287
20
- - eval_runtime: 63.0506
21
- - eval_samples_per_second: 30.15
22
- - eval_steps_per_second: 3.775
23
- - epoch: 11.76
24
- - step: 3200
25
 
26
  ## Model description
27
 
@@ -41,13 +38,57 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 0.0001
44
- - train_batch_size: 16
45
  - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 1000
50
- - num_epochs: 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
  ### Framework versions
53
 
 
3
  base_model: facebook/wav2vec2-base-100h
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: wav2vec2-base-timit-demo-google-colab
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base-100h](https://huggingface.co/facebook/wav2vec2-base-100h) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1428
21
+ - Wer: 0.1265
 
 
 
 
 
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0001
41
+ - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
+ - num_epochs: 10
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 6.924 | 0.26 | 200 | 4.0579 | 1.0 |
54
+ | 2.9378 | 0.51 | 400 | 1.9506 | 0.9319 |
55
+ | 1.4334 | 0.77 | 600 | 0.7472 | 0.4723 |
56
+ | 0.8152 | 1.03 | 800 | 0.5167 | 0.3405 |
57
+ | 0.6369 | 1.28 | 1000 | 0.3825 | 0.2747 |
58
+ | 0.4931 | 1.54 | 1200 | 0.3361 | 0.2407 |
59
+ | 0.4986 | 1.8 | 1400 | 0.3224 | 0.2228 |
60
+ | 0.392 | 2.05 | 1600 | 0.2876 | 0.2086 |
61
+ | 0.3527 | 2.31 | 1800 | 0.3104 | 0.2089 |
62
+ | 0.3171 | 2.57 | 2000 | 0.2431 | 0.1821 |
63
+ | 0.2847 | 2.82 | 2200 | 0.2153 | 0.1776 |
64
+ | 0.3274 | 3.08 | 2400 | 0.2486 | 0.1679 |
65
+ | 0.2901 | 3.34 | 2600 | 0.3754 | 0.1627 |
66
+ | 0.2539 | 3.59 | 2800 | 0.2790 | 0.1642 |
67
+ | 0.2427 | 3.85 | 3000 | 0.2485 | 0.1664 |
68
+ | 0.1992 | 4.11 | 3200 | 0.2184 | 0.1574 |
69
+ | 0.2873 | 4.36 | 3400 | 0.1967 | 0.1547 |
70
+ | 0.2037 | 4.62 | 3600 | 0.2289 | 0.1506 |
71
+ | 0.1967 | 4.88 | 3800 | 0.2263 | 0.1506 |
72
+ | 0.2254 | 5.13 | 4000 | 0.1629 | 0.1463 |
73
+ | 0.1808 | 5.39 | 4200 | 0.2015 | 0.1476 |
74
+ | 0.1762 | 5.65 | 4400 | 0.1948 | 0.1456 |
75
+ | 0.1829 | 5.91 | 4600 | 0.1521 | 0.1437 |
76
+ | 0.1934 | 6.16 | 4800 | 0.1638 | 0.1431 |
77
+ | 0.1643 | 6.42 | 5000 | 0.1476 | 0.1435 |
78
+ | 0.1244 | 6.68 | 5200 | 0.1937 | 0.1394 |
79
+ | 0.1615 | 6.93 | 5400 | 0.1508 | 0.1366 |
80
+ | 0.1708 | 7.19 | 5600 | 0.1298 | 0.1348 |
81
+ | 0.1736 | 7.45 | 5800 | 0.1383 | 0.1344 |
82
+ | 0.1429 | 7.7 | 6000 | 0.1711 | 0.1330 |
83
+ | 0.1453 | 7.96 | 6200 | 0.1844 | 0.1302 |
84
+ | 0.1387 | 8.22 | 6400 | 0.3321 | 0.1297 |
85
+ | 0.1259 | 8.47 | 6600 | 0.1617 | 0.1296 |
86
+ | 0.0874 | 8.73 | 6800 | 0.1432 | 0.1270 |
87
+ | 0.1107 | 8.99 | 7000 | 0.1302 | 0.1280 |
88
+ | 0.1205 | 9.24 | 7200 | 0.1461 | 0.1270 |
89
+ | 0.109 | 9.5 | 7400 | 0.1415 | 0.1271 |
90
+ | 0.1117 | 9.76 | 7600 | 0.1428 | 0.1265 |
91
+
92
 
93
  ### Framework versions
94
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:233c670d377ba4baf606b32d7e052660a4795d09ae80f940d98eb35612d1c7cc
3
  size 377658785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f45ea33eee8d332241209d333f65d4595bb153183d1c18257cfef297d47378
3
  size 377658785
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f36d1251f14347462d9764cdc11c706c46adfb015fdb6f267a29041c3cc230
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86fd4d55f0c6f71819bce95374cd43a1df1e3faa1403ede2d2c6a0407ee39c8a
3
  size 4091