Hugging Face's logo

nrshoudi
/
XLS-R_Jibbali_lang

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nrshoudi commited on
Commit
0abbbca
•
1 Parent(s): bbc7d45

End of training

Browse files
Files changed (4) hide show
  1. README.md +25 -24
  2. model.safetensors +1 -1
  3. runs/Feb17_16-30-34_96309f846a0a/events.out.tfevents.1708187470.96309f846a0a.1921.1 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1714
21
- - Wer: 0.1941
 
22
 
23
  ## Model description
24
 
@@ -51,28 +52,28 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Wer |
55
- |:-------------:|:-----:|:----:|:---------------:|:------:|
56
- | 16.1473 | 0.99 | 56 | 11.0651 | 1.0 |
57
- | 3.9177 | 2.0 | 113 | 3.4720 | 1.0 |
58
- | 3.1902 | 2.99 | 169 | 3.1574 | 1.0 |
59
- | 3.1711 | 4.0 | 226 | 3.1379 | 1.0 |
60
- | 3.1491 | 4.99 | 282 | 3.1154 | 1.0 |
61
- | 3.1449 | 6.0 | 339 | 3.0533 | 1.0 |
62
- | 2.9214 | 6.99 | 395 | 2.7533 | 1.0 |
63
- | 1.9003 | 8.0 | 452 | 1.4168 | 0.9291 |
64
- | 0.6151 | 8.99 | 508 | 0.3110 | 0.3224 |
65
- | 0.2125 | 10.0 | 565 | 0.2170 | 0.2145 |
66
- | 0.1754 | 10.99 | 621 | 0.1987 | 0.2069 |
67
- | 0.1688 | 12.0 | 678 | 0.1870 | 0.1985 |
68
- | 0.1012 | 12.99 | 734 | 0.1856 | 0.1908 |
69
- | 0.1157 | 14.0 | 791 | 0.1906 | 0.2025 |
70
- | 0.1427 | 14.99 | 847 | 0.1844 | 0.1937 |
71
- | 0.0513 | 16.0 | 904 | 0.1852 | 0.1915 |
72
- | 0.1403 | 16.99 | 960 | 0.1713 | 0.1944 |
73
- | 0.1119 | 18.0 | 1017 | 0.1610 | 0.1974 |
74
- | 0.1034 | 18.99 | 1073 | 0.1697 | 0.1944 |
75
- | 0.0428 | 19.82 | 1120 | 0.1714 | 0.1941 |
76
 
77
 
78
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1752
21
+ - Wer: 0.1926
22
+ - Cer: 0.0770
23
 
24
  ## Model description
25
 
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
56
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
57
+ | 16.5992 | 0.99 | 56 | 15.4050 | 1.0 | 0.9812 |
58
+ | 3.79 | 2.0 | 113 | 3.3988 | 1.0 | 0.9812 |
59
+ | 3.1872 | 2.99 | 169 | 3.1498 | 1.0 | 0.9812 |
60
+ | 3.1705 | 4.0 | 226 | 3.1354 | 1.0 | 0.9812 |
61
+ | 3.1147 | 4.99 | 282 | 3.0947 | 1.0 | 0.9812 |
62
+ | 3.0616 | 6.0 | 339 | 2.9447 | 1.0 | 0.9460 |
63
+ | 2.8239 | 6.99 | 395 | 2.6661 | 1.0 | 0.9106 |
64
+ | 1.5494 | 8.0 | 452 | 1.0992 | 0.8684 | 0.3804 |
65
+ | 0.5291 | 8.99 | 508 | 0.2822 | 0.3026 | 0.1004 |
66
+ | 0.2022 | 10.0 | 565 | 0.2019 | 0.2080 | 0.0665 |
67
+ | 0.1721 | 10.99 | 621 | 0.2067 | 0.2032 | 0.0841 |
68
+ | 0.1705 | 12.0 | 678 | 0.1968 | 0.1996 | 0.0728 |
69
+ | 0.0989 | 12.99 | 734 | 0.2038 | 0.1955 | 0.0821 |
70
+ | 0.1299 | 14.0 | 791 | 0.1814 | 0.1963 | 0.0837 |
71
+ | 0.1352 | 14.99 | 847 | 0.1896 | 0.1941 | 0.0768 |
72
+ | 0.0487 | 16.0 | 904 | 0.1951 | 0.1933 | 0.0749 |
73
+ | 0.1412 | 16.99 | 960 | 0.1650 | 0.1970 | 0.0818 |
74
+ | 0.1027 | 18.0 | 1017 | 0.1720 | 0.1941 | 0.0783 |
75
+ | 0.0791 | 18.99 | 1073 | 0.1730 | 0.1933 | 0.0767 |
76
+ | 0.0406 | 19.82 | 1120 | 0.1752 | 0.1926 | 0.0770 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3851d108e2cd1bfebf6683bee7d73484968f55bc1fba0598ecac36a643b35ea
3
  size 1261971480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222dba2b447a01883d048bb2e5061180969e6b66b5baf63cbfcc2449d777fca5
3
  size 1261971480
runs/Feb17_16-30-34_96309f846a0a/events.out.tfevents.1708187470.96309f846a0a.1921.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136dd6d10f8516967fa116a9974ef4b6f4d820d9f7320188d7344805ae618054
3
+ size 31102
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a885757fbfd1eecfe55fc6924474fa7cfa4de2e3a354551aec49e2bee72af741
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58f90f3709a4f27c53620454ce037244da21e863ff870fb883e6a0021c5ccea
3
  size 4600