Hugging Face's logo

yacoubagbane
/
checkpoints

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
yacoubagbane commited on
Commit
8f16497
·
verified ·
1 Parent(s): 1beed4d

yacoubagbane/wav2vec2-base-timit-dyula_koumankan_new_regex_UNIV

Browse files
Files changed (2) hide show
  1. README.md +10 -18
  2. model.safetensors +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-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.8440
22
- - Wer: 0.8471
23
 
24
  ## Model description
25
 
@@ -50,22 +50,14 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-------:|:----:|:---------------:|:------:|
55
- | 5.2882 | 0.7962 | 500 | 3.0818 | 1.0 |
56
- | 2.1156 | 1.5924 | 1000 | 1.8269 | 0.9243 |
57
- | 1.5045 | 2.3885 | 1500 | 1.6462 | 0.883 |
58
- | 1.3346 | 3.1847 | 2000 | 1.5850 | 0.8725 |
59
- | 1.2459 | 3.9809 | 2500 | 1.5096 | 0.8451 |
60
- | 1.1498 | 4.7771 | 3000 | 1.5949 | 0.8427 |
61
- | 1.0867 | 5.5732 | 3500 | 1.5995 | 0.8213 |
62
- | 1.0427 | 6.3694 | 4000 | 1.5592 | 0.8244 |
63
- | 0.9884 | 7.1656 | 4500 | 1.5782 | 0.8113 |
64
- | 0.9380 | 7.9618 | 5000 | 1.7195 | 0.8268 |
65
- | 0.8799 | 8.7580 | 5500 | 1.7174 | 0.8207 |
66
- | 0.8320 | 9.5541 | 6000 | 1.7601 | 0.8261 |
67
- | 0.7904 | 10.3503 | 6500 | 1.7749 | 0.8493 |
68
- | 0.7460 | 11.1465 | 7000 | 1.8440 | 0.8471 |
69
 
70
 
71
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.1084
22
+ - Wer: 1.0
23
 
24
  ## Model description
25
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:---:|
55
+ | 5.4567 | 0.7962 | 500 | 3.1191 | 1.0 |
56
+ | 3.0371 | 1.5924 | 1000 | 3.1471 | 1.0 |
57
+ | 3.0352 | 2.3885 | 1500 | 3.1423 | 1.0 |
58
+ | 3.0396 | 3.1847 | 2000 | 3.1056 | 1.0 |
59
+ | 3.0361 | 3.9809 | 2500 | 3.1074 | 1.0 |
60
+ | 3.0391 | 4.7771 | 3000 | 3.1084 | 1.0 |
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73e6273743ef416e2db7dbad749ec270ed061ffd5a61c0113aa383a321cb4761
3
  size 377706428
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb0ea4da0d53f6d8a7d667dc63859f0fd29f347395999274ed0ab306c35e8de
3
  size 377706428