Mustafaa4a commited on
Commit
fc2e79f
·
1 Parent(s): 14eb05a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -0
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: ASR-Somali
7
  results: []
@@ -13,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
13
  # ASR-Somali
14
 
15
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
 
 
 
16
 
17
  ## Model description
18
 
@@ -43,6 +48,23 @@ The following hyperparameters were used during training:
43
  - num_epochs: 30
44
  - mixed_precision_training: Native AMP
45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  ### Framework versions
47
 
48
  - Transformers 4.28.0
 
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
+ metrics:
6
+ - wer
7
  model-index:
8
  - name: ASR-Somali
9
  results: []
 
15
  # ASR-Somali
16
 
17
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.3660
20
+ - Wer: 0.3060
21
 
22
  ## Model description
23
 
 
48
  - num_epochs: 30
49
  - mixed_precision_training: Native AMP
50
 
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 3.1435 | 2.09 | 400 | 0.7624 | 0.7706 |
56
+ | 0.5829 | 4.18 | 800 | 0.3646 | 0.3935 |
57
+ | 0.3634 | 6.27 | 1200 | 0.3318 | 0.3944 |
58
+ | 0.2942 | 8.36 | 1600 | 0.3148 | 0.3403 |
59
+ | 0.2419 | 10.44 | 2000 | 0.3000 | 0.3255 |
60
+ | 0.2104 | 12.53 | 2400 | 0.2951 | 0.3312 |
61
+ | 0.1864 | 14.62 | 2800 | 0.3296 | 0.3083 |
62
+ | 0.1666 | 16.71 | 3200 | 0.3264 | 0.3153 |
63
+ | 0.148 | 18.8 | 3600 | 0.3188 | 0.3028 |
64
+ | 0.1305 | 20.89 | 4000 | 0.3448 | 0.3002 |
65
+ | 0.1206 | 22.98 | 4400 | 0.3660 | 0.3060 |
66
+
67
+
68
  ### Framework versions
69
 
70
  - Transformers 4.28.0