Hugging Face's logo

xekri
/
wav2vec2-common_voice_13_0-eo-10

Automatic Speech Recognition
Transformers
PyTorch
Esperanto
wav2vec2
mozilla-foundation/common_voice_13_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
xekri commited on
Commit
d1f35b5
•
1 Parent(s): 096891d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +100 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_13_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: wav2vec2-common_voice_13_0-eo-10
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_13_0
17
+ type: common_voice_13_0
18
+ config: eo
19
+ split: validation
20
+ args: eo
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.06575168361283507
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # wav2vec2-common_voice_13_0-eo-10
31
+
32
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0454
35
+ - Cer: 0.0119
36
+ - Wer: 0.0658
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 3e-05
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 32
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 500
64
+ - num_epochs: 5
65
+ - mixed_precision_training: Native AMP
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
70
+ |:-------------:|:-----:|:-----:|:------:|:---------------:|:------:|
71
+ | 2.9894 | 0.22 | 1000 | 1.0 | 2.9257 | 1.0 |
72
+ | 0.7104 | 0.44 | 2000 | 0.0457 | 0.2129 | 0.2538 |
73
+ | 0.2853 | 0.67 | 3000 | 0.0274 | 0.1109 | 0.1583 |
74
+ | 0.2327 | 0.89 | 4000 | 0.0231 | 0.0909 | 0.1320 |
75
+ | 0.1917 | 1.11 | 5000 | 0.0206 | 0.0775 | 0.1188 |
76
+ | 0.1803 | 1.33 | 6000 | 0.0184 | 0.0698 | 0.1055 |
77
+ | 0.1661 | 1.56 | 7000 | 0.0169 | 0.0645 | 0.0961 |
78
+ | 0.1635 | 1.78 | 8000 | 0.0170 | 0.0639 | 0.0964 |
79
+ | 0.1555 | 2.0 | 9000 | 0.0156 | 0.0592 | 0.0881 |
80
+ | 0.1386 | 2.22 | 10000 | 0.0147 | 0.0559 | 0.0821 |
81
+ | 0.1338 | 2.45 | 11000 | 0.0146 | 0.0548 | 0.0831 |
82
+ | 0.1307 | 2.67 | 12000 | 0.0137 | 0.0529 | 0.0759 |
83
+ | 0.1297 | 2.89 | 13000 | 0.0504 | 0.0134 | 0.0745 |
84
+ | 0.1201 | 3.11 | 14000 | 0.0499 | 0.0131 | 0.0734 |
85
+ | 0.1152 | 3.34 | 15000 | 0.0484 | 0.0128 | 0.0712 |
86
+ | 0.1144 | 3.56 | 16000 | 0.0477 | 0.0125 | 0.0695 |
87
+ | 0.1179 | 3.78 | 17000 | 0.0468 | 0.0122 | 0.0679 |
88
+ | 0.1112 | 4.0 | 18000 | 0.0468 | 0.0121 | 0.0676 |
89
+ | 0.1141 | 4.23 | 19000 | 0.0462 | 0.0121 | 0.0668 |
90
+ | 0.1085 | 4.45 | 20000 | 0.0458 | 0.0119 | 0.0664 |
91
+ | 0.105 | 4.67 | 21000 | 0.0456 | 0.0119 | 0.0660 |
92
+ | 0.1072 | 4.89 | 22000 | 0.0454 | 0.0119 | 0.0658 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.29.2
98
+ - Pytorch 2.0.1+cu117
99
+ - Datasets 2.12.0
100
+ - Tokenizers 0.13.3