tonyalves commited on
Commit
d5b303e
1 Parent(s): 75c55a0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -0
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: wav2vec2-300m-teste4
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
+ # wav2vec2-300m-teste4
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: 0.3276
20
+ - Wer: 0.3489
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: 4
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 10.0237 | 0.49 | 100 | 4.2075 | 0.9792 |
56
+ | 3.313 | 0.98 | 200 | 3.0232 | 0.9792 |
57
+ | 2.9469 | 1.47 | 300 | 2.7591 | 0.9792 |
58
+ | 1.4217 | 1.96 | 400 | 0.8397 | 0.6219 |
59
+ | 0.5598 | 2.45 | 500 | 0.6085 | 0.5087 |
60
+ | 0.4507 | 2.94 | 600 | 0.4512 | 0.4317 |
61
+ | 0.2775 | 3.43 | 700 | 0.3839 | 0.3751 |
62
+ | 0.2047 | 3.92 | 800 | 0.3276 | 0.3489 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.11.3
68
+ - Pytorch 1.9.1+cu102
69
+ - Datasets 1.17.0
70
+ - Tokenizers 0.10.3