Hugging Face's logo

kalmuraee
/
tokens

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
kalmuraee commited on
Commit
586273c
·
1 Parent(s): 08905d2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +112 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: tokens
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
+ # tokens
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: 0.9811
20
+ - Wer: 0.4608
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: 16
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: 30
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
55
+ | 6.5212 | 0.59 | 400 | 3.3776 | 1.0 |
56
+ | 2.4798 | 1.18 | 800 | 1.0697 | 0.7740 |
57
+ | 1.0057 | 1.77 | 1200 | 0.7077 | 0.6487 |
58
+ | 0.7731 | 2.36 | 1600 | 0.6113 | 0.5883 |
59
+ | 0.6917 | 2.94 | 2000 | 0.5618 | 0.5573 |
60
+ | 0.5844 | 3.53 | 2400 | 0.5610 | 0.5532 |
61
+ | 0.5606 | 4.12 | 2800 | 0.5584 | 0.5484 |
62
+ | 0.4973 | 4.71 | 3200 | 0.5466 | 0.5333 |
63
+ | 0.4721 | 5.3 | 3600 | 0.5495 | 0.5178 |
64
+ | 0.4439 | 5.89 | 4000 | 0.5667 | 0.5237 |
65
+ | 0.3965 | 6.48 | 4400 | 0.5865 | 0.5322 |
66
+ | 0.3876 | 7.07 | 4800 | 0.6099 | 0.5135 |
67
+ | 0.3407 | 7.66 | 5200 | 0.5891 | 0.5228 |
68
+ | 0.33 | 8.25 | 5600 | 0.6135 | 0.5072 |
69
+ | 0.3032 | 8.84 | 6000 | 0.6004 | 0.5028 |
70
+ | 0.2706 | 9.43 | 6400 | 0.6321 | 0.4991 |
71
+ | 0.2709 | 10.01 | 6800 | 0.6541 | 0.5051 |
72
+ | 0.2373 | 10.6 | 7200 | 0.6613 | 0.5119 |
73
+ | 0.2284 | 11.19 | 7600 | 0.6798 | 0.5086 |
74
+ | 0.212 | 11.78 | 8000 | 0.6509 | 0.4910 |
75
+ | 0.1983 | 12.37 | 8400 | 0.7018 | 0.5043 |
76
+ | 0.1947 | 12.96 | 8800 | 0.6826 | 0.4965 |
77
+ | 0.1717 | 13.55 | 9200 | 0.7056 | 0.4828 |
78
+ | 0.1741 | 14.14 | 9600 | 0.7544 | 0.5060 |
79
+ | 0.1626 | 14.73 | 10000 | 0.7331 | 0.4915 |
80
+ | 0.1529 | 15.32 | 10400 | 0.7518 | 0.4772 |
81
+ | 0.1504 | 15.91 | 10800 | 0.7362 | 0.4732 |
82
+ | 0.1401 | 16.49 | 11200 | 0.7179 | 0.4769 |
83
+ | 0.1335 | 17.08 | 11600 | 0.7716 | 0.4826 |
84
+ | 0.1185 | 17.67 | 12000 | 0.7465 | 0.4798 |
85
+ | 0.1182 | 18.26 | 12400 | 0.8105 | 0.4733 |
86
+ | 0.1135 | 18.85 | 12800 | 0.7693 | 0.4743 |
87
+ | 0.1098 | 19.44 | 13200 | 0.8362 | 0.4888 |
88
+ | 0.1023 | 20.03 | 13600 | 0.8427 | 0.4768 |
89
+ | 0.1003 | 20.62 | 14000 | 0.8079 | 0.4741 |
90
+ | 0.0936 | 21.21 | 14400 | 0.8551 | 0.4651 |
91
+ | 0.0875 | 21.8 | 14800 | 0.8462 | 0.4712 |
92
+ | 0.0843 | 22.39 | 15200 | 0.9177 | 0.4782 |
93
+ | 0.0846 | 22.97 | 15600 | 0.8618 | 0.4735 |
94
+ | 0.08 | 23.56 | 16000 | 0.9017 | 0.4687 |
95
+ | 0.0789 | 24.15 | 16400 | 0.9034 | 0.4659 |
96
+ | 0.0717 | 24.74 | 16800 | 0.9690 | 0.4734 |
97
+ | 0.0714 | 25.33 | 17200 | 0.9395 | 0.4677 |
98
+ | 0.0699 | 25.92 | 17600 | 0.9222 | 0.4608 |
99
+ | 0.0658 | 26.51 | 18000 | 0.9222 | 0.4621 |
100
+ | 0.0612 | 27.1 | 18400 | 0.9691 | 0.4586 |
101
+ | 0.0583 | 27.69 | 18800 | 0.9647 | 0.4581 |
102
+ | 0.0596 | 28.28 | 19200 | 0.9820 | 0.4614 |
103
+ | 0.056 | 28.87 | 19600 | 0.9795 | 0.4596 |
104
+ | 0.055 | 29.45 | 20000 | 0.9811 | 0.4608 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.11.3
110
+ - Pytorch 1.10.0+cu113
111
+ - Datasets 1.18.3
112
+ - Tokenizers 0.10.3