anuragshas commited on
Commit
466bfc4
1 Parent(s): ebfc7fa

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +76 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: ''
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
+ #
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 common_voice dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1893
20
+ - Wer: 0.2003
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: 7.5e-05
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 16
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: 60.0
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 3.4219 | 3.6 | 400 | 3.3127 | 1.0 |
54
+ | 3.0399 | 7.21 | 800 | 3.0330 | 1.0 |
55
+ | 1.5756 | 10.81 | 1200 | 0.6108 | 0.5724 |
56
+ | 1.0995 | 14.41 | 1600 | 0.3091 | 0.3154 |
57
+ | 0.9639 | 18.02 | 2000 | 0.2596 | 0.2841 |
58
+ | 0.9032 | 21.62 | 2400 | 0.2270 | 0.2514 |
59
+ | 0.8145 | 25.23 | 2800 | 0.2172 | 0.2483 |
60
+ | 0.7845 | 28.83 | 3200 | 0.2084 | 0.2333 |
61
+ | 0.7694 | 32.43 | 3600 | 0.1974 | 0.2234 |
62
+ | 0.7333 | 36.04 | 4000 | 0.2020 | 0.2185 |
63
+ | 0.693 | 39.64 | 4400 | 0.1947 | 0.2148 |
64
+ | 0.6802 | 43.24 | 4800 | 0.1960 | 0.2102 |
65
+ | 0.667 | 46.85 | 5200 | 0.1904 | 0.2072 |
66
+ | 0.6486 | 50.45 | 5600 | 0.1881 | 0.2009 |
67
+ | 0.6339 | 54.05 | 6000 | 0.1877 | 0.1989 |
68
+ | 0.6254 | 57.66 | 6400 | 0.1893 | 0.2003 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.17.0.dev0
74
+ - Pytorch 1.10.2+cu102
75
+ - Datasets 1.18.2.dev0
76
+ - Tokenizers 0.11.0