Hugging Face's logo

monadical-labs
/
wav2vec2-large-960h

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
ilokavat commited on
Commit
e18ac6f
·
verified ·
1 Parent(s): ed89ad8

End of training

Browse files
Files changed (3) hide show
  1. README.md +20 -7
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-large-960h](https://huggingface.co/facebook/wav2vec2-large-960h) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.6166
22
- - Wer: 0.4851
23
 
24
  ## Model description
25
 
@@ -39,7 +39,7 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 0.0001
42
- - train_batch_size: 32
43
  - eval_batch_size: 8
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
@@ -50,10 +50,23 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 0.9616 | 50.0 | 50 | 1.4023 | 0.4636 |
56
- | 0.1974 | 100.0 | 100 | 1.6166 | 0.4851 |
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-large-960h](https://huggingface.co/facebook/wav2vec2-large-960h) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6286
22
+ - Wer: 0.1538
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 0.0001
42
+ - train_batch_size: 64
43
  - eval_batch_size: 8
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:--------:|:----:|:---------------:|:------:|
55
+ | 1.2379 | 8.3333 | 50 | 0.6501 | 0.3056 |
56
+ | 0.4865 | 16.6667 | 100 | 0.7069 | 0.2790 |
57
+ | 0.3054 | 25.0 | 150 | 0.6598 | 0.2369 |
58
+ | 0.2308 | 33.3333 | 200 | 0.6517 | 0.2215 |
59
+ | 0.1793 | 41.6667 | 250 | 0.6884 | 0.2103 |
60
+ | 0.1379 | 50.0 | 300 | 0.6418 | 0.1949 |
61
+ | 0.1253 | 58.3333 | 350 | 0.7004 | 0.1918 |
62
+ | 0.0988 | 66.6667 | 400 | 0.6059 | 0.1846 |
63
+ | 0.088 | 75.0 | 450 | 0.6507 | 0.1826 |
64
+ | 0.0773 | 83.3333 | 500 | 0.5473 | 0.1682 |
65
+ | 0.0686 | 91.6667 | 550 | 0.6027 | 0.1682 |
66
+ | 0.0643 | 100.0 | 600 | 0.6192 | 0.1713 |
67
+ | 0.0595 | 108.3333 | 650 | 0.6119 | 0.1703 |
68
+ | 0.0562 | 116.6667 | 700 | 0.5953 | 0.16 |
69
+ | 0.0507 | 125.0 | 750 | 0.6286 | 0.1538 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aaac7bb182b2ea5859e59146064d481e2bf6e89ed65cc46f079cc0f5a700fc2
3
  size 1261897368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b63ba50d14faad6d45c6e0e4618afa60ea1b5acb542b28c85450c5b21c7d2b
3
  size 1261897368
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:980beecbaebdafe0030be46fa2d590aa8ef2ce857e5babc506df24690fdeb412
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:994caeb9a0eb03004707562f39667ce24d93cf69b73e47e1eb61b78c4fd081c0
3
  size 5368