elsayedissa commited on
Commit
ebfcc72
1 Parent(s): e643b2a

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
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: wav2vec2-xls-r-300m-ar
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
+ # wav2vec2-xls-r-300m-ar
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.3212
20
+ - Wer: 0.0636
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: 0.0003
40
+ - train_batch_size: 16
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: 500
46
+ - training_steps: 10000
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
52
+ | 0.0793 | 8.85 | 1000 | 0.1626 | 0.0786 |
53
+ | 0.0396 | 17.7 | 2000 | 0.2199 | 0.0807 |
54
+ | 0.0285 | 26.55 | 3000 | 0.2289 | 0.0694 |
55
+ | 0.021 | 35.4 | 4000 | 0.2662 | 0.0722 |
56
+ | 0.0177 | 44.25 | 5000 | 0.2459 | 0.0744 |
57
+ | 0.0155 | 53.1 | 6000 | 0.2689 | 0.0679 |
58
+ | 0.0149 | 61.95 | 7000 | 0.2760 | 0.0717 |
59
+ | 0.0074 | 70.8 | 8000 | 0.3004 | 0.0680 |
60
+ | 0.0058 | 79.65 | 9000 | 0.3113 | 0.0650 |
61
+ | 0.0033 | 88.5 | 10000 | 0.3212 | 0.0636 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.28.0.dev0
67
+ - Pytorch 2.0.0+cu117
68
+ - Datasets 2.11.1.dev0
69
+ - Tokenizers 0.13.2