Hugging Face's logo

utakumi
/
Hubert-common_voice_JSUT-ja-demo-kana

Automatic Speech Recognition
Transformers
Safetensors
Japanese
hubert
mozilla-foundation/common_voice_13_0
Generated from Trainer
Inference Endpoints
Model card Files Community
utakumi commited on
Commit
2556e0d
·
verified ·
1 Parent(s): 9de812e

Model save

Browse files
Files changed (1) hide show
  1. README.md +168 -0
README.md ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: rinna/japanese-hubert-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: Hubert-common_voice_JSUT-ja-demo-kana
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Hubert-common_voice_JSUT-ja-demo-kana
18
+
19
+ This model is a fine-tuned version of [rinna/japanese-hubert-base](https://huggingface.co/rinna/japanese-hubert-base) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.5777
22
+ - Wer: 1.0
23
+ - Cer: 0.3109
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 3e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 32
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_steps: 12500
51
+ - num_epochs: 20.0
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
58
+ | No log | 0.1936 | 100 | 41.9560 | 1.5294 | 6.1696 |
59
+ | No log | 0.3872 | 200 | 41.4657 | 1.4235 | 5.9722 |
60
+ | No log | 0.5808 | 300 | 40.2769 | 1.1848 | 3.7327 |
61
+ | No log | 0.7744 | 400 | 36.3010 | 1.0 | 0.9963 |
62
+ | 31.4419 | 0.9681 | 500 | 24.5426 | 1.0 | 0.9991 |
63
+ | 31.4419 | 1.1607 | 600 | 18.8642 | 1.0 | 0.9991 |
64
+ | 31.4419 | 1.3543 | 700 | 17.6651 | 1.0 | 0.9991 |
65
+ | 31.4419 | 1.5479 | 800 | 17.2007 | 1.0 | 0.9992 |
66
+ | 31.4419 | 1.7415 | 900 | 16.7617 | 1.0 | 0.9991 |
67
+ | 14.8315 | 1.9351 | 1000 | 16.2895 | 1.0 | 0.9991 |
68
+ | 14.8315 | 2.1278 | 1100 | 15.7877 | 1.0 | 0.9991 |
69
+ | 14.8315 | 2.3214 | 1200 | 15.2488 | 1.0 | 0.9991 |
70
+ | 14.8315 | 2.5150 | 1300 | 14.6680 | 1.0 | 0.9991 |
71
+ | 14.8315 | 2.7086 | 1400 | 14.0637 | 1.0 | 0.9991 |
72
+ | 12.4363 | 2.9022 | 1500 | 13.4217 | 1.0 | 0.9991 |
73
+ | 12.4363 | 3.0949 | 1600 | 12.7374 | 1.0 | 0.9991 |
74
+ | 12.4363 | 3.2885 | 1700 | 12.0319 | 1.0 | 0.9991 |
75
+ | 12.4363 | 3.4821 | 1800 | 11.2982 | 1.0 | 0.9991 |
76
+ | 12.4363 | 3.6757 | 1900 | 10.5580 | 1.0 | 0.9992 |
77
+ | 9.8267 | 3.8693 | 2000 | 9.8129 | 1.0 | 0.9991 |
78
+ | 9.8267 | 4.0620 | 2100 | 9.0640 | 1.0 | 0.9991 |
79
+ | 9.8267 | 4.2556 | 2200 | 8.3376 | 1.0 | 0.9992 |
80
+ | 9.8267 | 4.4492 | 2300 | 7.6287 | 1.0 | 0.9991 |
81
+ | 9.8267 | 4.6428 | 2400 | 6.9678 | 1.0 | 0.9991 |
82
+ | 6.9778 | 4.8364 | 2500 | 6.3635 | 1.0 | 0.9992 |
83
+ | 6.9778 | 5.0290 | 2600 | 5.8258 | 1.0 | 0.9991 |
84
+ | 6.9778 | 5.2227 | 2700 | 5.3677 | 1.0 | 0.9991 |
85
+ | 6.9778 | 5.4163 | 2800 | 4.9888 | 1.0 | 0.9991 |
86
+ | 6.9778 | 5.6099 | 2900 | 4.6956 | 1.0 | 0.9991 |
87
+ | 4.8731 | 5.8035 | 3000 | 4.4788 | 1.0 | 0.9991 |
88
+ | 4.8731 | 5.9971 | 3100 | 4.3287 | 1.0 | 0.9991 |
89
+ | 4.8731 | 6.1897 | 3200 | 4.2057 | 1.0 | 0.9991 |
90
+ | 4.8731 | 6.3833 | 3300 | 4.1448 | 1.0 | 0.9991 |
91
+ | 4.8731 | 6.5770 | 3400 | 4.1095 | 1.0 | 0.9991 |
92
+ | 4.1216 | 6.7706 | 3500 | 4.0858 | 1.0 | 0.9991 |
93
+ | 4.1216 | 6.9642 | 3600 | 4.0725 | 1.0 | 0.9991 |
94
+ | 4.1216 | 7.1568 | 3700 | 4.0648 | 1.0 | 0.9991 |
95
+ | 4.1216 | 7.3504 | 3800 | 4.0578 | 1.0 | 0.9991 |
96
+ | 4.1216 | 7.5440 | 3900 | 4.0494 | 1.0 | 0.9991 |
97
+ | 4.0264 | 7.7377 | 4000 | 4.0367 | 1.0 | 0.9991 |
98
+ | 4.0264 | 7.9313 | 4100 | 4.0276 | 1.0 | 0.9991 |
99
+ | 4.0264 | 8.1239 | 4200 | 4.0121 | 1.0 | 0.9991 |
100
+ | 4.0264 | 8.3175 | 4300 | 3.9720 | 1.0 | 0.9991 |
101
+ | 4.0264 | 8.5111 | 4400 | 3.9031 | 1.0 | 0.9991 |
102
+ | 3.937 | 8.7047 | 4500 | 3.8091 | 1.0 | 0.9991 |
103
+ | 3.937 | 8.8984 | 4600 | 3.6690 | 1.0 | 0.9991 |
104
+ | 3.937 | 9.0910 | 4700 | 3.4759 | 1.0 | 0.9991 |
105
+ | 3.937 | 9.2846 | 4800 | 3.2108 | 1.0 | 0.9987 |
106
+ | 3.937 | 9.4782 | 4900 | 2.6813 | 1.0 | 0.6453 |
107
+ | 3.1866 | 9.6718 | 5000 | 2.3876 | 1.0002 | 0.5372 |
108
+ | 3.1866 | 9.8654 | 5100 | 2.1678 | 1.0 | 0.4902 |
109
+ | 3.1866 | 10.0581 | 5200 | 1.9945 | 1.0002 | 0.4530 |
110
+ | 3.1866 | 10.2517 | 5300 | 1.8576 | 1.0 | 0.4270 |
111
+ | 3.1866 | 10.4453 | 5400 | 1.7788 | 1.0 | 0.4399 |
112
+ | 1.9458 | 10.6389 | 5500 | 1.6520 | 1.0 | 0.4094 |
113
+ | 1.9458 | 10.8325 | 5600 | 1.5545 | 1.0 | 0.3874 |
114
+ | 1.9458 | 11.0252 | 5700 | 1.4698 | 1.0 | 0.3800 |
115
+ | 1.9458 | 11.2188 | 5800 | 1.4052 | 1.0 | 0.3777 |
116
+ | 1.9458 | 11.4124 | 5900 | 1.3276 | 1.0 | 0.3658 |
117
+ | 1.4263 | 11.6060 | 6000 | 1.2710 | 1.0 | 0.3668 |
118
+ | 1.4263 | 11.7996 | 6100 | 1.2150 | 1.0 | 0.3536 |
119
+ | 1.4263 | 11.9932 | 6200 | 1.1586 | 1.0 | 0.3531 |
120
+ | 1.4263 | 12.1859 | 6300 | 1.1156 | 1.0 | 0.3519 |
121
+ | 1.4263 | 12.3795 | 6400 | 1.0729 | 1.0 | 0.3484 |
122
+ | 1.1212 | 12.5731 | 6500 | 1.0345 | 1.0 | 0.3467 |
123
+ | 1.1212 | 12.7667 | 6600 | 0.9887 | 1.0 | 0.3428 |
124
+ | 1.1212 | 12.9603 | 6700 | 0.9630 | 1.0 | 0.3417 |
125
+ | 1.1212 | 13.1530 | 6800 | 0.9260 | 1.0 | 0.3381 |
126
+ | 1.1212 | 13.3466 | 6900 | 0.9005 | 1.0 | 0.3397 |
127
+ | 0.9141 | 13.5402 | 7000 | 0.8764 | 1.0 | 0.3369 |
128
+ | 0.9141 | 13.7338 | 7100 | 0.8512 | 1.0 | 0.3363 |
129
+ | 0.9141 | 13.9274 | 7200 | 0.8273 | 1.0 | 0.3351 |
130
+ | 0.9141 | 14.1200 | 7300 | 0.8083 | 1.0 | 0.3329 |
131
+ | 0.9141 | 14.3136 | 7400 | 0.7851 | 0.9998 | 0.3300 |
132
+ | 0.7811 | 14.5073 | 7500 | 0.7743 | 1.0 | 0.3312 |
133
+ | 0.7811 | 14.7009 | 7600 | 0.7510 | 0.9998 | 0.3272 |
134
+ | 0.7811 | 14.8945 | 7700 | 0.7366 | 1.0 | 0.3267 |
135
+ | 0.7811 | 15.0871 | 7800 | 0.7290 | 1.0 | 0.3253 |
136
+ | 0.7811 | 15.2807 | 7900 | 0.7132 | 1.0 | 0.3247 |
137
+ | 0.6725 | 15.4743 | 8000 | 0.7190 | 1.0 | 0.3277 |
138
+ | 0.6725 | 15.6680 | 8100 | 0.7006 | 1.0 | 0.3241 |
139
+ | 0.6725 | 15.8616 | 8200 | 0.6835 | 1.0 | 0.3226 |
140
+ | 0.6725 | 16.0542 | 8300 | 0.6698 | 0.9998 | 0.3209 |
141
+ | 0.6725 | 16.2478 | 8400 | 0.6628 | 0.9998 | 0.3214 |
142
+ | 0.606 | 16.4414 | 8500 | 0.6538 | 1.0 | 0.3205 |
143
+ | 0.606 | 16.6350 | 8600 | 0.6523 | 1.0 | 0.3186 |
144
+ | 0.606 | 16.8287 | 8700 | 0.6449 | 1.0 | 0.3183 |
145
+ | 0.606 | 17.0213 | 8800 | 0.6401 | 1.0 | 0.3179 |
146
+ | 0.606 | 17.2149 | 8900 | 0.6333 | 1.0 | 0.3200 |
147
+ | 0.5492 | 17.4085 | 9000 | 0.6333 | 1.0 | 0.3201 |
148
+ | 0.5492 | 17.6021 | 9100 | 0.6219 | 1.0 | 0.3179 |
149
+ | 0.5492 | 17.7957 | 9200 | 0.6189 | 1.0 | 0.3201 |
150
+ | 0.5492 | 17.9894 | 9300 | 0.6023 | 0.9998 | 0.3166 |
151
+ | 0.5492 | 18.1820 | 9400 | 0.6084 | 1.0 | 0.3154 |
152
+ | 0.5057 | 18.3756 | 9500 | 0.6002 | 0.9998 | 0.3147 |
153
+ | 0.5057 | 18.5692 | 9600 | 0.5875 | 1.0 | 0.3128 |
154
+ | 0.5057 | 18.7628 | 9700 | 0.5903 | 0.9998 | 0.3138 |
155
+ | 0.5057 | 18.9564 | 9800 | 0.5930 | 1.0 | 0.3127 |
156
+ | 0.5057 | 19.1491 | 9900 | 0.5855 | 1.0 | 0.3141 |
157
+ | 0.4709 | 19.3427 | 10000 | 0.5880 | 1.0 | 0.3120 |
158
+ | 0.4709 | 19.5363 | 10100 | 0.5855 | 1.0 | 0.3131 |
159
+ | 0.4709 | 19.7299 | 10200 | 0.5734 | 1.0 | 0.3106 |
160
+ | 0.4709 | 19.9235 | 10300 | 0.5777 | 1.0 | 0.3109 |
161
+
162
+
163
+ ### Framework versions
164
+
165
+ - Transformers 4.47.0.dev0
166
+ - Pytorch 2.5.1+cu124
167
+ - Datasets 3.1.0
168
+ - Tokenizers 0.20.3