Hugging Face's logo

zoha
/
wav2vec2-xlsr-persian-50p

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
zoha commited on
Commit
e780f1e
·
1 Parent(s): 8ba3a43

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-xlsr-persian-50p
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-xlsr-persian-50p
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.6846
18
+ - Wer: 0.4339
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: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 16
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 500
46
+ - num_epochs: 30
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | No log | 1.05 | 250 | 3.2104 | 1.0 |
54
+ | 3.2437 | 2.11 | 500 | 2.9131 | 1.0 |
55
+ | 3.2437 | 3.16 | 750 | 1.0335 | 0.7303 |
56
+ | 1.4382 | 4.22 | 1000 | 0.8335 | 0.6155 |
57
+ | 1.4382 | 5.27 | 1250 | 0.7640 | 0.5904 |
58
+ | 0.6923 | 6.33 | 1500 | 0.6923 | 0.5468 |
59
+ | 0.6923 | 7.38 | 1750 | 0.6627 | 0.5238 |
60
+ | 0.5137 | 8.44 | 2000 | 0.6606 | 0.5112 |
61
+ | 0.5137 | 9.49 | 2250 | 0.6600 | 0.5125 |
62
+ | 0.4258 | 10.55 | 2500 | 0.6337 | 0.4939 |
63
+ | 0.4258 | 11.6 | 2750 | 0.6454 | 0.4851 |
64
+ | 0.362 | 12.66 | 3000 | 0.6481 | 0.4793 |
65
+ | 0.362 | 13.71 | 3250 | 0.6487 | 0.4801 |
66
+ | 0.3179 | 14.77 | 3500 | 0.6602 | 0.4668 |
67
+ | 0.3179 | 15.82 | 3750 | 0.6757 | 0.4683 |
68
+ | 0.2861 | 16.88 | 4000 | 0.6544 | 0.4591 |
69
+ | 0.2861 | 17.93 | 4250 | 0.6659 | 0.4634 |
70
+ | 0.2529 | 18.99 | 4500 | 0.6311 | 0.4556 |
71
+ | 0.2529 | 20.04 | 4750 | 0.6574 | 0.4525 |
72
+ | 0.235 | 21.1 | 5000 | 0.7019 | 0.4462 |
73
+ | 0.235 | 22.15 | 5250 | 0.6783 | 0.4426 |
74
+ | 0.2203 | 23.21 | 5500 | 0.6789 | 0.4361 |
75
+ | 0.2203 | 24.26 | 5750 | 0.6779 | 0.4336 |
76
+ | 0.2014 | 25.32 | 6000 | 0.6805 | 0.4406 |
77
+ | 0.2014 | 26.37 | 6250 | 0.6918 | 0.4407 |
78
+ | 0.1957 | 27.43 | 6500 | 0.6919 | 0.4360 |
79
+ | 0.1957 | 28.48 | 6750 | 0.6795 | 0.4332 |
80
+ | 0.1837 | 29.53 | 7000 | 0.6846 | 0.4339 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.11.3
86
+ - Pytorch 1.10.0+cu113
87
+ - Datasets 1.18.3
88
+ - Tokenizers 0.10.3