Hugging Face's logo

utakumi
/
Hubert-common_voice-ja-demo-kana-only-cosine

Automatic Speech Recognition
Transformers
Safetensors
Japanese
hubert
mozilla-foundation/common_voice_13_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
utakumi commited on
Commit
cee5e01
·
verified ·
1 Parent(s): 4a67ded

Model save

Browse files
Files changed (1) hide show
  1. README.md +174 -0
README.md ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: rinna/japanese-hubert-base
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - common_voice_13_0
9
+ metrics:
10
+ - wer
11
+ model-index:
12
+ - name: Hubert-common_voice-ja-demo-kana-only-cosine
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: 1.0
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
+ # Hubert-common_voice-ja-demo-kana-only-cosine
33
+
34
+ This model is a fine-tuned version of [rinna/japanese-hubert-base](https://huggingface.co/rinna/japanese-hubert-base) on the common_voice_13_0 dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.6323
37
+ - Wer: 1.0
38
+ - Cer: 0.3307
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: 3e-05
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: cosine
65
+ - lr_scheduler_warmup_steps: 12500
66
+ - num_epochs: 25.0
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 | 43.2251 | 1.5295 | 5.8210 |
74
+ | No log | 0.5319 | 200 | 42.4452 | 1.5322 | 5.2849 |
75
+ | No log | 0.7979 | 300 | 40.4154 | 1.1262 | 1.8126 |
76
+ | No log | 1.0638 | 400 | 32.8021 | 1.0 | 0.9999 |
77
+ | 31.884 | 1.3298 | 500 | 20.8133 | 1.0 | 0.9999 |
78
+ | 31.884 | 1.5957 | 600 | 17.5824 | 1.0 | 0.9999 |
79
+ | 31.884 | 1.8617 | 700 | 16.8682 | 1.0 | 0.9999 |
80
+ | 31.884 | 2.1277 | 800 | 16.4466 | 1.0 | 0.9999 |
81
+ | 31.884 | 2.3936 | 900 | 16.0037 | 1.0 | 0.9999 |
82
+ | 14.4701 | 2.6596 | 1000 | 15.5409 | 1.0 | 0.9999 |
83
+ | 14.4701 | 2.9255 | 1100 | 15.0446 | 1.0 | 0.9999 |
84
+ | 14.4701 | 3.1915 | 1200 | 14.5023 | 1.0 | 0.9999 |
85
+ | 14.4701 | 3.4574 | 1300 | 13.9298 | 1.0 | 0.9999 |
86
+ | 14.4701 | 3.7234 | 1400 | 13.3212 | 1.0 | 0.9999 |
87
+ | 12.1626 | 3.9894 | 1500 | 12.6814 | 1.0 | 0.9999 |
88
+ | 12.1626 | 4.2553 | 1600 | 12.0099 | 1.0 | 0.9999 |
89
+ | 12.1626 | 4.5213 | 1700 | 11.3179 | 1.0 | 0.9999 |
90
+ | 12.1626 | 4.7872 | 1800 | 10.6017 | 1.0 | 0.9999 |
91
+ | 12.1626 | 5.0532 | 1900 | 9.8810 | 1.0 | 0.9999 |
92
+ | 9.5127 | 5.3191 | 2000 | 9.1567 | 1.0 | 0.9999 |
93
+ | 9.5127 | 5.5851 | 2100 | 8.4445 | 1.0 | 0.9999 |
94
+ | 9.5127 | 5.8511 | 2200 | 7.7573 | 1.0 | 0.9999 |
95
+ | 9.5127 | 6.1170 | 2300 | 7.1049 | 1.0 | 0.9999 |
96
+ | 9.5127 | 6.3830 | 2400 | 6.5016 | 1.0 | 0.9999 |
97
+ | 6.6873 | 6.6489 | 2500 | 5.9565 | 1.0 | 0.9999 |
98
+ | 6.6873 | 6.9149 | 2600 | 5.4853 | 1.0 | 0.9999 |
99
+ | 6.6873 | 7.1809 | 2700 | 5.0997 | 1.0 | 0.9999 |
100
+ | 6.6873 | 7.4468 | 2800 | 4.7889 | 1.0 | 0.9999 |
101
+ | 6.6873 | 7.7128 | 2900 | 4.5573 | 1.0 | 0.9999 |
102
+ | 4.7448 | 7.9787 | 3000 | 4.3889 | 1.0 | 0.9999 |
103
+ | 4.7448 | 8.2447 | 3100 | 4.2614 | 1.0 | 0.9999 |
104
+ | 4.7448 | 8.5106 | 3200 | 4.1960 | 1.0 | 0.9999 |
105
+ | 4.7448 | 8.7766 | 3300 | 4.1398 | 1.0 | 0.9999 |
106
+ | 4.7448 | 9.0426 | 3400 | 4.1092 | 1.0 | 0.9999 |
107
+ | 4.1253 | 9.3085 | 3500 | 4.0911 | 1.0 | 0.9999 |
108
+ | 4.1253 | 9.5745 | 3600 | 4.0851 | 1.0 | 0.9999 |
109
+ | 4.1253 | 9.8404 | 3700 | 4.0707 | 1.0 | 0.9999 |
110
+ | 4.1253 | 10.1064 | 3800 | 4.0630 | 1.0 | 0.9999 |
111
+ | 4.1253 | 10.3723 | 3900 | 4.0589 | 1.0 | 0.9999 |
112
+ | 4.0399 | 10.6383 | 4000 | 4.0574 | 1.0 | 0.9999 |
113
+ | 4.0399 | 10.9043 | 4100 | 4.0495 | 1.0 | 0.9999 |
114
+ | 4.0399 | 11.1702 | 4200 | 4.0367 | 1.0 | 0.9999 |
115
+ | 4.0399 | 11.4362 | 4300 | 4.0297 | 1.0 | 0.9999 |
116
+ | 4.0399 | 11.7021 | 4400 | 4.0168 | 1.0 | 0.9999 |
117
+ | 4.0102 | 11.9681 | 4500 | 4.0002 | 1.0 | 0.9999 |
118
+ | 4.0102 | 12.2340 | 4600 | 3.9823 | 1.0 | 0.9999 |
119
+ | 4.0102 | 12.5 | 4700 | 3.9474 | 1.0 | 0.9999 |
120
+ | 4.0102 | 12.7660 | 4800 | 3.8870 | 1.0 | 0.9999 |
121
+ | 4.0102 | 13.0319 | 4900 | 3.7933 | 1.0 | 0.9999 |
122
+ | 3.8616 | 13.2979 | 5000 | 3.6576 | 1.0 | 0.9999 |
123
+ | 3.8616 | 13.5638 | 5100 | 3.4925 | 1.0 | 0.9999 |
124
+ | 3.8616 | 13.8298 | 5200 | 3.2550 | 1.0 | 0.9999 |
125
+ | 3.8616 | 14.0957 | 5300 | 2.8836 | 1.0 | 0.8301 |
126
+ | 3.8616 | 14.3617 | 5400 | 2.5211 | 1.0 | 0.6171 |
127
+ | 3.023 | 14.6277 | 5500 | 2.2902 | 1.0 | 0.5481 |
128
+ | 3.023 | 14.8936 | 5600 | 2.1006 | 1.0 | 0.5079 |
129
+ | 3.023 | 15.1596 | 5700 | 1.9464 | 1.0 | 0.4784 |
130
+ | 3.023 | 15.4255 | 5800 | 1.8196 | 1.0 | 0.4597 |
131
+ | 3.023 | 15.6915 | 5900 | 1.6975 | 1.0 | 0.4238 |
132
+ | 1.9348 | 15.9574 | 6000 | 1.6040 | 1.0 | 0.4093 |
133
+ | 1.9348 | 16.2234 | 6100 | 1.5035 | 1.0 | 0.4021 |
134
+ | 1.9348 | 16.4894 | 6200 | 1.4211 | 1.0 | 0.3930 |
135
+ | 1.9348 | 16.7553 | 6300 | 1.3529 | 1.0 | 0.3802 |
136
+ | 1.9348 | 17.0213 | 6400 | 1.2795 | 1.0 | 0.3791 |
137
+ | 1.4128 | 17.2872 | 6500 | 1.2193 | 1.0 | 0.3711 |
138
+ | 1.4128 | 17.5532 | 6600 | 1.1646 | 1.0 | 0.3674 |
139
+ | 1.4128 | 17.8191 | 6700 | 1.1193 | 1.0 | 0.3706 |
140
+ | 1.4128 | 18.0851 | 6800 | 1.0665 | 1.0 | 0.3606 |
141
+ | 1.4128 | 18.3511 | 6900 | 1.0244 | 0.9998 | 0.3590 |
142
+ | 1.1012 | 18.6170 | 7000 | 0.9864 | 1.0 | 0.3540 |
143
+ | 1.1012 | 18.8830 | 7100 | 0.9578 | 1.0 | 0.3554 |
144
+ | 1.1012 | 19.1489 | 7200 | 0.9309 | 0.9998 | 0.3509 |
145
+ | 1.1012 | 19.4149 | 7300 | 0.9070 | 1.0 | 0.3495 |
146
+ | 1.1012 | 19.6809 | 7400 | 0.8693 | 0.9998 | 0.3470 |
147
+ | 0.9083 | 19.9468 | 7500 | 0.8492 | 1.0 | 0.3449 |
148
+ | 0.9083 | 20.2128 | 7600 | 0.8214 | 1.0 | 0.3449 |
149
+ | 0.9083 | 20.4787 | 7700 | 0.8211 | 1.0 | 0.3500 |
150
+ | 0.9083 | 20.7447 | 7800 | 0.7964 | 1.0 | 0.3452 |
151
+ | 0.9083 | 21.0106 | 7900 | 0.7797 | 1.0 | 0.3429 |
152
+ | 0.7546 | 21.2766 | 8000 | 0.7634 | 1.0 | 0.3400 |
153
+ | 0.7546 | 21.5426 | 8100 | 0.7471 | 1.0 | 0.3384 |
154
+ | 0.7546 | 21.8085 | 8200 | 0.7400 | 1.0 | 0.3378 |
155
+ | 0.7546 | 22.0745 | 8300 | 0.7214 | 1.0 | 0.3390 |
156
+ | 0.7546 | 22.3404 | 8400 | 0.7062 | 0.9998 | 0.3375 |
157
+ | 0.651 | 22.6064 | 8500 | 0.6973 | 1.0 | 0.3344 |
158
+ | 0.651 | 22.8723 | 8600 | 0.6930 | 0.9998 | 0.3344 |
159
+ | 0.651 | 23.1383 | 8700 | 0.6829 | 1.0 | 0.3350 |
160
+ | 0.651 | 23.4043 | 8800 | 0.6683 | 1.0 | 0.3332 |
161
+ | 0.651 | 23.6702 | 8900 | 0.6596 | 0.9998 | 0.3322 |
162
+ | 0.5868 | 23.9362 | 9000 | 0.6764 | 1.0 | 0.3321 |
163
+ | 0.5868 | 24.2021 | 9100 | 0.6635 | 0.9998 | 0.3308 |
164
+ | 0.5868 | 24.4681 | 9200 | 0.6560 | 1.0 | 0.3324 |
165
+ | 0.5868 | 24.7340 | 9300 | 0.6412 | 1.0 | 0.3290 |
166
+ | 0.5868 | 25.0 | 9400 | 0.6323 | 1.0 | 0.3307 |
167
+
168
+
169
+ ### Framework versions
170
+
171
+ - Transformers 4.47.0.dev0
172
+ - Pytorch 2.5.1+cu124
173
+ - Datasets 3.1.0
174
+ - Tokenizers 0.20.3