bryan6aero commited on
Commit
6ac7954
1 Parent(s): 4ac74cd

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-base-timit-demo-colab
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # wav2vec2-base-timit-demo-colab
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.4678
18
+ - Wer: 0.3415
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 30
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
51
+ | 3.4531 | 4.0 | 500 | 1.2397 | 0.8576 |
52
+ | 0.5827 | 8.0 | 1000 | 0.4529 | 0.4364 |
53
+ | 0.2161 | 12.0 | 1500 | 0.4630 | 0.3992 |
54
+ | 0.1278 | 16.0 | 2000 | 0.4307 | 0.3709 |
55
+ | 0.09 | 20.0 | 2500 | 0.4772 | 0.3611 |
56
+ | 0.0634 | 24.0 | 3000 | 0.4338 | 0.3462 |
57
+ | 0.0467 | 28.0 | 3500 | 0.4678 | 0.3415 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.11.3
63
+ - Pytorch 1.10.0+cu111
64
+ - Datasets 1.18.3
65
+ - Tokenizers 0.10.3