Hugging Face's logo

Baybars
/
wav2vec2-xls-r-1b-turkish

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Turkish
wav2vec2
common_voice
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
Baybars commited on
Commit
1c15eee
•
1 Parent(s): 7e05a35

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -32
README.md CHANGED
@@ -1,9 +1,5 @@
1
  ---
2
- language:
3
- - tr
4
  tags:
5
- - automatic-speech-recognition
6
- - common_voice
7
  - generated_from_trainer
8
  datasets:
9
  - common_voice
@@ -17,11 +13,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  #
19
 
20
- This model is a fine-tuned version of [./checkpoint-10500](https://huggingface.co/./checkpoint-10500) on the COMMON_VOICE - TR dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.7360
23
- - Wer: 0.4754
24
- - Cer: 0.1339
25
 
26
  ## Model description
27
 
@@ -46,34 +42,39 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.999,0.9999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 5.0
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
55
- |:-------------:|:-----:|:-----:|:------:|:---------------:|:------:|
56
- | 1.0779 | 4.59 | 500 | 0.2354 | 0.8260 | 0.7395 |
57
- | 0.7573 | 9.17 | 1000 | 0.2100 | 0.7544 | 0.6960 |
58
- | 0.8225 | 13.76 | 1500 | 0.2021 | 0.6867 | 0.6672 |
59
- | 0.621 | 18.35 | 2000 | 0.1874 | 0.6824 | 0.6209 |
60
- | 0.6362 | 22.94 | 2500 | 0.1904 | 0.6712 | 0.6286 |
61
- | 0.624 | 27.52 | 3000 | 0.1820 | 0.6940 | 0.6116 |
62
- | 0.4781 | 32.11 | 3500 | 0.1735 | 0.6966 | 0.5989 |
63
- | 0.5685 | 36.7 | 4000 | 0.1769 | 0.6742 | 0.5971 |
64
- | 0.4384 | 41.28 | 4500 | 0.1767 | 0.6904 | 0.5999 |
65
- | 0.5509 | 45.87 | 5000 | 0.1692 | 0.6734 | 0.5641 |
66
- | 0.3665 | 50.46 | 5500 | 0.1680 | 0.7018 | 0.5662 |
67
- | 0.3914 | 55.05 | 6000 | 0.1631 | 0.7121 | 0.5552 |
68
- | 0.2467 | 59.63 | 6500 | 0.1563 | 0.6657 | 0.5374 |
69
- | 0.2576 | 64.22 | 7000 | 0.1554 | 0.6920 | 0.5316 |
70
- | 0.2711 | 68.81 | 7500 | 0.1495 | 0.6900 | 0.5176 |
71
- | 0.2626 | 73.39 | 8000 | 0.1454 | 0.6843 | 0.5043 |
72
- | 0.1377 | 77.98 | 8500 | 0.1470 | 0.7383 | 0.5101 |
73
- | 0.2005 | 82.57 | 9000 | 0.1430 | 0.7228 | 0.5045 |
74
- | 0.1355 | 87.16 | 9500 | 0.1375 | 0.7231 | 0.4869 |
75
- | 0.0431 | 91.74 | 10000 | 0.1350 | 0.7397 | 0.4749 |
76
- | 0.0586 | 96.33 | 10500 | 0.1339 | 0.7360 | 0.4754 |
 
 
 
 
 
77
 
78
 
79
  ### Framework versions
 
1
  ---
 
 
2
  tags:
 
 
3
  - generated_from_trainer
4
  datasets:
5
  - common_voice
 
13
 
14
  #
15
 
16
+ This model is a fine-tuned version of [./checkpoint-10500](https://huggingface.co/./checkpoint-10500) on the common_voice dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.7535
19
+ - Wer: 0.4651
20
+ - Cer: 0.1317
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.999,0.9999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 120.0
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
51
+ |:-------------:|:------:|:-----:|:------:|:---------------:|:------:|
52
+ | 1.0779 | 4.59 | 500 | 0.2354 | 0.8260 | 0.7395 |
53
+ | 0.7573 | 9.17 | 1000 | 0.2100 | 0.7544 | 0.6960 |
54
+ | 0.8225 | 13.76 | 1500 | 0.2021 | 0.6867 | 0.6672 |
55
+ | 0.621 | 18.35 | 2000 | 0.1874 | 0.6824 | 0.6209 |
56
+ | 0.6362 | 22.94 | 2500 | 0.1904 | 0.6712 | 0.6286 |
57
+ | 0.624 | 27.52 | 3000 | 0.1820 | 0.6940 | 0.6116 |
58
+ | 0.4781 | 32.11 | 3500 | 0.1735 | 0.6966 | 0.5989 |
59
+ | 0.5685 | 36.7 | 4000 | 0.1769 | 0.6742 | 0.5971 |
60
+ | 0.4384 | 41.28 | 4500 | 0.1767 | 0.6904 | 0.5999 |
61
+ | 0.5509 | 45.87 | 5000 | 0.1692 | 0.6734 | 0.5641 |
62
+ | 0.3665 | 50.46 | 5500 | 0.1680 | 0.7018 | 0.5662 |
63
+ | 0.3914 | 55.05 | 6000 | 0.1631 | 0.7121 | 0.5552 |
64
+ | 0.2467 | 59.63 | 6500 | 0.1563 | 0.6657 | 0.5374 |
65
+ | 0.2576 | 64.22 | 7000 | 0.1554 | 0.6920 | 0.5316 |
66
+ | 0.2711 | 68.81 | 7500 | 0.1495 | 0.6900 | 0.5176 |
67
+ | 0.2626 | 73.39 | 8000 | 0.1454 | 0.6843 | 0.5043 |
68
+ | 0.1377 | 77.98 | 8500 | 0.1470 | 0.7383 | 0.5101 |
69
+ | 0.2005 | 82.57 | 9000 | 0.1430 | 0.7228 | 0.5045 |
70
+ | 0.1355 | 87.16 | 9500 | 0.1375 | 0.7231 | 0.4869 |
71
+ | 0.0431 | 91.74 | 10000 | 0.1350 | 0.7397 | 0.4749 |
72
+ | 0.0586 | 96.33 | 10500 | 0.1339 | 0.7360 | 0.4754 |
73
+ | 0.0896 | 100.92 | 11000 | 0.7187 | 0.4885 | 0.1398 |
74
+ | 0.183 | 105.5 | 11500 | 0.7310 | 0.4838 | 0.1392 |
75
+ | 0.0963 | 110.09 | 12000 | 0.7643 | 0.4759 | 0.1362 |
76
+ | 0.0437 | 114.68 | 12500 | 0.7525 | 0.4641 | 0.1328 |
77
+ | 0.1122 | 119.27 | 13000 | 0.7535 | 0.4651 | 0.1317 |
78
 
79
 
80
  ### Framework versions