Hugging Face's logo

yacoubagbane
/
checkpoints

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
yacoubagbane commited on
Commit
37aa024
·
verified ·
1 Parent(s): 57d4434

yacoubagbane/wav2vec2-base-timit-dyula_koumankan_new_regex_UNIV

Browse files
Files changed (2) hide show
  1. README.md +18 -10
  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: 3.1096
22
- - Wer: 1.0
23
 
24
  ## Model description
25
 
@@ -50,14 +50,22 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:------:|:----:|:---------------:|:---:|
55
- | 5.4694 | 0.7962 | 500 | 3.0959 | 1.0 |
56
- | 3.0230 | 1.5924 | 1000 | 3.1457 | 1.0 |
57
- | 3.0390 | 2.3885 | 1500 | 3.1315 | 1.0 |
58
- | 3.0412 | 3.1847 | 2000 | 3.1064 | 1.0 |
59
- | 3.0370 | 3.9809 | 2500 | 3.1075 | 1.0 |
60
- | 3.0401 | 4.7771 | 3000 | 3.1096 | 1.0 |
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### 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: 1.9349
22
+ - Wer: 0.8429
23
 
24
  ## Model description
25
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-------:|:----:|:---------------:|:------:|
55
+ | 5.4705 | 0.7962 | 500 | 3.0918 | 1.0 |
56
+ | 2.3153 | 1.5924 | 1000 | 1.9470 | 0.937 |
57
+ | 1.5547 | 2.3885 | 1500 | 1.6620 | 0.8839 |
58
+ | 1.3604 | 3.1847 | 2000 | 1.5991 | 0.8663 |
59
+ | 1.2648 | 3.9809 | 2500 | 1.5240 | 0.8471 |
60
+ | 1.1763 | 4.7771 | 3000 | 1.6433 | 0.8594 |
61
+ | 1.1084 | 5.5732 | 3500 | 1.5223 | 0.8255 |
62
+ | 1.0614 | 6.3694 | 4000 | 1.5046 | 0.8253 |
63
+ | 1.0154 | 7.1656 | 4500 | 1.6364 | 0.8187 |
64
+ | 0.9633 | 7.9618 | 5000 | 1.5997 | 0.8247 |
65
+ | 0.9058 | 8.7580 | 5500 | 1.6880 | 0.8254 |
66
+ | 0.8616 | 9.5541 | 6000 | 1.7325 | 0.8258 |
67
+ | 0.8303 | 10.3503 | 6500 | 1.6496 | 0.8275 |
68
+ | 0.7738 | 11.1465 | 7000 | 1.9349 | 0.8429 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9f7477f56a4bf43aea697846bc1d6fb3aa875a5a753cfa4db0b76d5ecec922
3
  size 377706428
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e104b19a881bd624229bdbe0eefbb199ad6b949f75dbeec3451b24b525179621
3
  size 377706428