Hugging Face's logo

xekri
/
wav2vec2-common_voice_13_0-eo-3

Automatic Speech Recognition
Transformers
PyTorch
Esperanto
wav2vec2
mozilla-foundation/common_voice_13_0
Generated from Trainer
Inference Endpoints
Model card Files Community
xekri commited on
Commit
adc9aa0
•
1 Parent(s): 5bc575c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +109 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: wav2vec2-common_voice_13_0-eo-3
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-common_voice_13_0-eo-3
16
+
17
+ 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.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2191
20
+ - Cer: 0.0208
21
+ - Wer: 0.0686
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-06
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 500
49
+ - num_epochs: 100
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
55
+ |:-------------:|:-----:|:-----:|:------:|:---------------:|:------:|
56
+ | 2.6416 | 2.13 | 1000 | 0.1541 | 0.8599 | 0.6449 |
57
+ | 0.2633 | 4.27 | 2000 | 0.0335 | 0.1897 | 0.1431 |
58
+ | 0.1739 | 6.4 | 3000 | 0.0289 | 0.1732 | 0.1145 |
59
+ | 0.1378 | 8.53 | 4000 | 0.0276 | 0.1729 | 0.1066 |
60
+ | 0.1172 | 10.67 | 5000 | 0.0268 | 0.1773 | 0.1019 |
61
+ | 0.1049 | 12.8 | 6000 | 0.0255 | 0.1701 | 0.0937 |
62
+ | 0.0951 | 14.93 | 7000 | 0.0253 | 0.1718 | 0.0933 |
63
+ | 0.0851 | 17.07 | 8000 | 0.0239 | 0.1787 | 0.0834 |
64
+ | 0.0809 | 19.2 | 9000 | 0.0235 | 0.1802 | 0.0835 |
65
+ | 0.0756 | 21.33 | 10000 | 0.0239 | 0.1784 | 0.0855 |
66
+ | 0.0708 | 23.47 | 11000 | 0.0235 | 0.1748 | 0.0824 |
67
+ | 0.0657 | 25.6 | 12000 | 0.0228 | 0.1830 | 0.0796 |
68
+ | 0.0605 | 27.73 | 13000 | 0.0230 | 0.1896 | 0.0798 |
69
+ | 0.0583 | 29.87 | 14000 | 0.0224 | 0.1889 | 0.0778 |
70
+ | 0.0608 | 32.0 | 15000 | 0.0223 | 0.1849 | 0.0757 |
71
+ | 0.0556 | 34.13 | 16000 | 0.0223 | 0.1872 | 0.0767 |
72
+ | 0.0534 | 36.27 | 17000 | 0.0221 | 0.1893 | 0.0751 |
73
+ | 0.0523 | 38.4 | 18000 | 0.0218 | 0.1925 | 0.0729 |
74
+ | 0.0494 | 40.53 | 19000 | 0.0221 | 0.1957 | 0.0745 |
75
+ | 0.0475 | 42.67 | 20000 | 0.0217 | 0.1961 | 0.0740 |
76
+ | 0.048 | 44.8 | 21000 | 0.0214 | 0.1957 | 0.0714 |
77
+ | 0.0459 | 46.93 | 22000 | 0.0215 | 0.1968 | 0.0717 |
78
+ | 0.0435 | 49.07 | 23000 | 0.0217 | 0.2008 | 0.0717 |
79
+ | 0.0428 | 51.2 | 24000 | 0.0212 | 0.1991 | 0.0696 |
80
+ | 0.0418 | 53.33 | 25000 | 0.0215 | 0.2034 | 0.0714 |
81
+ | 0.0404 | 55.47 | 26000 | 0.0210 | 0.2014 | 0.0684 |
82
+ | 0.0394 | 57.6 | 27000 | 0.0210 | 0.2050 | 0.0681 |
83
+ | 0.0399 | 59.73 | 28000 | 0.0211 | 0.2039 | 0.0700 |
84
+ | 0.0389 | 61.87 | 29000 | 0.0214 | 0.2091 | 0.0694 |
85
+ | 0.038 | 64.0 | 30000 | 0.0210 | 0.2100 | 0.0702 |
86
+ | 0.0361 | 66.13 | 31000 | 0.0215 | 0.2119 | 0.0703 |
87
+ | 0.0359 | 68.27 | 32000 | 0.0213 | 0.2108 | 0.0714 |
88
+ | 0.0354 | 70.4 | 33000 | 0.0211 | 0.2120 | 0.0699 |
89
+ | 0.0364 | 72.53 | 34000 | 0.0211 | 0.2128 | 0.0688 |
90
+ | 0.0361 | 74.67 | 35000 | 0.0212 | 0.2134 | 0.0694 |
91
+ | 0.0332 | 76.8 | 36000 | 0.0210 | 0.2176 | 0.0698 |
92
+ | 0.0341 | 78.93 | 37000 | 0.0208 | 0.2170 | 0.0688 |
93
+ | 0.032 | 81.07 | 38000 | 0.0209 | 0.2157 | 0.0686 |
94
+ | 0.0318 | 83.33 | 39000 | 0.0209 | 0.2166 | 0.0685 |
95
+ | 0.0325 | 85.47 | 40000 | 0.2172 | 0.0209 | 0.0687 |
96
+ | 0.0316 | 87.6 | 41000 | 0.2181 | 0.0208 | 0.0678 |
97
+ | 0.0302 | 89.73 | 42000 | 0.2171 | 0.0208 | 0.0679 |
98
+ | 0.0318 | 91.87 | 43000 | 0.2179 | 0.0211 | 0.0702 |
99
+ | 0.0314 | 94.0 | 44000 | 0.2186 | 0.0208 | 0.0690 |
100
+ | 0.0309 | 96.13 | 45000 | 0.2193 | 0.0210 | 0.0696 |
101
+ | 0.031 | 98.27 | 46000 | 0.2191 | 0.0208 | 0.0686 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.29.1
107
+ - Pytorch 2.0.1+cu118
108
+ - Datasets 2.12.0
109
+ - Tokenizers 0.13.3