1ucky40nc3 commited on
Commit
8baae56
1 Parent(s): b96e6eb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +78 -0
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: wav2vec2-common_voice-tr-demo
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-common_voice-tr-demo
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 dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.3807
20
+ - Wer: 0.3456
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
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 32
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 15.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | No log | 0.92 | 100 | 3.5932 | 1.0 |
56
+ | No log | 1.83 | 200 | 3.0185 | 0.9999 |
57
+ | No log | 2.75 | 300 | 0.9357 | 0.8007 |
58
+ | No log | 3.67 | 400 | 0.5945 | 0.6318 |
59
+ | 3.1829 | 4.59 | 500 | 0.4931 | 0.5265 |
60
+ | 3.1829 | 5.5 | 600 | 0.4757 | 0.4784 |
61
+ | 3.1829 | 6.42 | 700 | 0.4282 | 0.4540 |
62
+ | 3.1829 | 7.34 | 800 | 0.3995 | 0.4252 |
63
+ | 3.1829 | 8.26 | 900 | 0.4046 | 0.4149 |
64
+ | 0.2215 | 9.17 | 1000 | 0.4048 | 0.3951 |
65
+ | 0.2215 | 10.09 | 1100 | 0.3944 | 0.3865 |
66
+ | 0.2215 | 11.01 | 1200 | 0.3853 | 0.3643 |
67
+ | 0.2215 | 11.93 | 1300 | 0.3950 | 0.3632 |
68
+ | 0.2215 | 12.84 | 1400 | 0.3836 | 0.3506 |
69
+ | 0.1009 | 13.76 | 1500 | 0.3808 | 0.3510 |
70
+ | 0.1009 | 14.68 | 1600 | 0.3807 | 0.3456 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.22.0.dev0
76
+ - Pytorch 1.12.1+cu102
77
+ - Datasets 2.4.0
78
+ - Tokenizers 0.12.1