Hugging Face's logo

utakumi
/
wav2vec2-large-xlsr-53-common_voice-ja-demo-kana-only

Automatic Speech Recognition
Transformers
Safetensors
Japanese
wav2vec2
mozilla-foundation/common_voice_13_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
utakumi commited on
Commit
6c69659
·
verified ·
1 Parent(s): 8ae3dd7

Model save

Browse files
Files changed (2) hide show
  1. README.md +136 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/wav2vec2-large-xlsr-53
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - common_voice_13_0
9
+ metrics:
10
+ - wer
11
+ model-index:
12
+ - name: wav2vec2-large-xlsr-53-common_voice-ja-demo-kana-only
13
+ results:
14
+ - task:
15
+ name: Automatic Speech Recognition
16
+ type: automatic-speech-recognition
17
+ dataset:
18
+ name: common_voice_13_0
19
+ type: common_voice_13_0
20
+ config: ja
21
+ split: test
22
+ args: ja
23
+ metrics:
24
+ - name: Wer
25
+ type: wer
26
+ value: 0.9997984277363435
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # wav2vec2-large-xlsr-53-common_voice-ja-demo-kana-only
33
+
34
+ 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.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.6984
37
+ - Wer: 0.9998
38
+ - Cer: 0.3127
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 0.0003
58
+ - train_batch_size: 16
59
+ - eval_batch_size: 8
60
+ - seed: 42
61
+ - gradient_accumulation_steps: 2
62
+ - total_train_batch_size: 32
63
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
64
+ - lr_scheduler_type: linear
65
+ - lr_scheduler_warmup_steps: 500
66
+ - num_epochs: 15.0
67
+ - mixed_precision_training: Native AMP
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
72
+ |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
73
+ | No log | 0.2660 | 100 | 6.8309 | 1.0 | 0.9999 |
74
+ | No log | 0.5319 | 200 | 4.1299 | 1.0 | 0.9999 |
75
+ | No log | 0.7979 | 300 | 3.9930 | 1.0 | 0.9869 |
76
+ | No log | 1.0638 | 400 | 2.0400 | 1.0 | 0.5876 |
77
+ | 7.1041 | 1.3298 | 500 | 1.0610 | 1.0 | 0.4309 |
78
+ | 7.1041 | 1.5957 | 600 | 0.8837 | 1.0 | 0.3955 |
79
+ | 7.1041 | 1.8617 | 700 | 0.7706 | 0.9998 | 0.3791 |
80
+ | 7.1041 | 2.1277 | 800 | 0.7662 | 1.0 | 0.3816 |
81
+ | 7.1041 | 2.3936 | 900 | 0.7621 | 1.0 | 0.3790 |
82
+ | 0.803 | 2.6596 | 1000 | 0.6969 | 1.0 | 0.3626 |
83
+ | 0.803 | 2.9255 | 1100 | 0.6736 | 1.0 | 0.3573 |
84
+ | 0.803 | 3.1915 | 1200 | 0.6823 | 0.9998 | 0.3544 |
85
+ | 0.803 | 3.4574 | 1300 | 0.6360 | 1.0 | 0.3460 |
86
+ | 0.803 | 3.7234 | 1400 | 0.6504 | 1.0 | 0.3443 |
87
+ | 0.5675 | 3.9894 | 1500 | 0.6247 | 1.0 | 0.3414 |
88
+ | 0.5675 | 4.2553 | 1600 | 0.6397 | 0.9998 | 0.3425 |
89
+ | 0.5675 | 4.5213 | 1700 | 0.6589 | 1.0 | 0.3439 |
90
+ | 0.5675 | 4.7872 | 1800 | 0.6345 | 1.0 | 0.3449 |
91
+ | 0.5675 | 5.0532 | 1900 | 0.6522 | 0.9996 | 0.3380 |
92
+ | 0.4421 | 5.3191 | 2000 | 0.6293 | 1.0 | 0.3372 |
93
+ | 0.4421 | 5.5851 | 2100 | 0.6096 | 1.0 | 0.3342 |
94
+ | 0.4421 | 5.8511 | 2200 | 0.6108 | 1.0 | 0.3321 |
95
+ | 0.4421 | 6.1170 | 2300 | 0.6200 | 1.0 | 0.3354 |
96
+ | 0.4421 | 6.3830 | 2400 | 0.6413 | 1.0 | 0.3341 |
97
+ | 0.3699 | 6.6489 | 2500 | 0.6303 | 0.9996 | 0.3359 |
98
+ | 0.3699 | 6.9149 | 2600 | 0.6013 | 1.0 | 0.3308 |
99
+ | 0.3699 | 7.1809 | 2700 | 0.6343 | 1.0 | 0.3286 |
100
+ | 0.3699 | 7.4468 | 2800 | 0.6208 | 0.9998 | 0.3260 |
101
+ | 0.3699 | 7.7128 | 2900 | 0.6095 | 0.9998 | 0.3287 |
102
+ | 0.3146 | 7.9787 | 3000 | 0.6058 | 0.9996 | 0.3266 |
103
+ | 0.3146 | 8.2447 | 3100 | 0.6613 | 0.9996 | 0.3251 |
104
+ | 0.3146 | 8.5106 | 3200 | 0.6539 | 1.0 | 0.3244 |
105
+ | 0.3146 | 8.7766 | 3300 | 0.6331 | 1.0 | 0.3264 |
106
+ | 0.3146 | 9.0426 | 3400 | 0.6436 | 1.0 | 0.3228 |
107
+ | 0.2576 | 9.3085 | 3500 | 0.6329 | 1.0 | 0.3235 |
108
+ | 0.2576 | 9.5745 | 3600 | 0.6315 | 0.9998 | 0.3197 |
109
+ | 0.2576 | 9.8404 | 3700 | 0.6281 | 0.9998 | 0.3203 |
110
+ | 0.2576 | 10.1064 | 3800 | 0.6696 | 0.9996 | 0.3196 |
111
+ | 0.2576 | 10.3723 | 3900 | 0.6630 | 0.9996 | 0.3199 |
112
+ | 0.2201 | 10.6383 | 4000 | 0.6781 | 1.0 | 0.3203 |
113
+ | 0.2201 | 10.9043 | 4100 | 0.6531 | 1.0 | 0.3196 |
114
+ | 0.2201 | 11.1702 | 4200 | 0.6763 | 0.9998 | 0.3193 |
115
+ | 0.2201 | 11.4362 | 4300 | 0.6785 | 1.0 | 0.3184 |
116
+ | 0.2201 | 11.7021 | 4400 | 0.6664 | 0.9998 | 0.3179 |
117
+ | 0.1931 | 11.9681 | 4500 | 0.6682 | 0.9998 | 0.3184 |
118
+ | 0.1931 | 12.2340 | 4600 | 0.6800 | 0.9998 | 0.3168 |
119
+ | 0.1931 | 12.5 | 4700 | 0.6925 | 1.0 | 0.3162 |
120
+ | 0.1931 | 12.7660 | 4800 | 0.7047 | 1.0 | 0.3145 |
121
+ | 0.1931 | 13.0319 | 4900 | 0.6919 | 0.9998 | 0.3147 |
122
+ | 0.1694 | 13.2979 | 5000 | 0.6999 | 0.9998 | 0.3142 |
123
+ | 0.1694 | 13.5638 | 5100 | 0.6995 | 1.0 | 0.3134 |
124
+ | 0.1694 | 13.8298 | 5200 | 0.6917 | 0.9998 | 0.3134 |
125
+ | 0.1694 | 14.0957 | 5300 | 0.6963 | 0.9998 | 0.3129 |
126
+ | 0.1694 | 14.3617 | 5400 | 0.6961 | 0.9998 | 0.3128 |
127
+ | 0.1548 | 14.6277 | 5500 | 0.6964 | 1.0 | 0.3129 |
128
+ | 0.1548 | 14.8936 | 5600 | 0.6984 | 0.9998 | 0.3127 |
129
+
130
+
131
+ ### Framework versions
132
+
133
+ - Transformers 4.47.0.dev0
134
+ - Pytorch 2.5.1+cu124
135
+ - Datasets 3.1.0
136
+ - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62653c305a0525283581483b3875fd54ac436aef31172e3fce9ba4eba48b4a2d
3
  size 1262160080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d01280b6aec63d9df34729f19ec4afd58d7493613f063c3def60704fcdfe8bd
3
  size 1262160080