Plim commited on
Commit
4ae460e
1 Parent(s): 4128b52

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +72 -0
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: ''
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
+ #
14
+
15
+ 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.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.2619
18
+ - Wer: 0.2457
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: 7.5e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 128
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 2000
46
+ - num_epochs: 2.0
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 3.495 | 0.16 | 500 | 3.3883 | 1.0 |
54
+ | 2.9095 | 0.32 | 1000 | 2.9152 | 1.0000 |
55
+ | 1.8434 | 0.49 | 1500 | 1.0473 | 0.7446 |
56
+ | 1.4298 | 0.65 | 2000 | 0.5729 | 0.5130 |
57
+ | 1.1937 | 0.81 | 2500 | 0.3795 | 0.3450 |
58
+ | 1.1248 | 0.97 | 3000 | 0.3321 | 0.3052 |
59
+ | 1.0835 | 1.13 | 3500 | 0.3038 | 0.2805 |
60
+ | 1.0479 | 1.3 | 4000 | 0.2910 | 0.2689 |
61
+ | 1.0413 | 1.46 | 4500 | 0.2798 | 0.2593 |
62
+ | 1.014 | 1.62 | 5000 | 0.2727 | 0.2512 |
63
+ | 1.004 | 1.78 | 5500 | 0.2646 | 0.2471 |
64
+ | 0.9949 | 1.94 | 6000 | 0.2619 | 0.2457 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.17.0.dev0
70
+ - Pytorch 1.10.2+cu102
71
+ - Datasets 1.18.2.dev0
72
+ - Tokenizers 0.11.0