hadiqa123 commited on
Commit
f1c6e8a
1 Parent(s): 0153e43

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_8_0
7
+ model-index:
8
+ - name: xls-r-ur-large
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # xls-r-ur-large
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 common_voice_8_0 dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8056
20
+ - Wer: 0.4716
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 1000
46
+ - num_epochs: 30
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 6.5282 | 3.25 | 1000 | 3.0650 | 0.9989 |
54
+ | 1.7351 | 6.49 | 2000 | 0.8798 | 0.6284 |
55
+ | 0.7662 | 9.74 | 3000 | 0.7720 | 0.5399 |
56
+ | 0.5675 | 12.99 | 4000 | 0.7661 | 0.5229 |
57
+ | 0.4591 | 16.23 | 5000 | 0.7849 | 0.5041 |
58
+ | 0.3881 | 19.48 | 6000 | 0.8065 | 0.4893 |
59
+ | 0.3522 | 22.73 | 7000 | 0.7915 | 0.4804 |
60
+ | 0.3127 | 25.97 | 8000 | 0.8119 | 0.4804 |
61
+ | 0.2932 | 29.22 | 9000 | 0.8056 | 0.4716 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.21.0
67
+ - Pytorch 1.11.0+cu113
68
+ - Datasets 2.4.0
69
+ - Tokenizers 0.12.1