Hugging Face's logo

utakumi
/
Hubert-common_voice_JSUT-ja-demo-japanese

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
5559bc3
•
1 Parent(s): a3212b4

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-japanese
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-japanese
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: 2.1762
22
+ - Wer: 1.9914
23
+ - Cer: 0.6413
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 | 0.1934 | 100 | 84.6958 | 1.0115 | 8.4850 |
59
+ | No log | 0.3868 | 200 | 83.7886 | 1.0090 | 8.3443 |
60
+ | No log | 0.5803 | 300 | 81.7457 | 1.0004 | 4.8157 |
61
+ | No log | 0.7737 | 400 | 75.4304 | 1.0 | 0.9907 |
62
+ | 66.0277 | 0.9671 | 500 | 63.1251 | 1.0 | 0.9907 |
63
+ | 66.0277 | 1.1605 | 600 | 57.1050 | 1.0 | 0.9907 |
64
+ | 66.0277 | 1.3540 | 700 | 55.6799 | 1.0 | 0.9908 |
65
+ | 66.0277 | 1.5474 | 800 | 55.0476 | 1.0 | 0.9907 |
66
+ | 66.0277 | 1.7408 | 900 | 54.4085 | 1.0 | 0.9907 |
67
+ | 46.3141 | 1.9342 | 1000 | 53.6893 | 1.0 | 0.9908 |
68
+ | 46.3141 | 2.1277 | 1100 | 52.9711 | 1.0 | 0.9907 |
69
+ | 46.3141 | 2.3211 | 1200 | 52.1326 | 1.0 | 0.9907 |
70
+ | 46.3141 | 2.5145 | 1300 | 51.2549 | 1.0 | 0.9907 |
71
+ | 46.3141 | 2.7079 | 1400 | 50.2649 | 1.0 | 0.9907 |
72
+ | 42.8642 | 2.9014 | 1500 | 49.2081 | 1.0 | 0.9907 |
73
+ | 42.8642 | 3.0948 | 1600 | 48.1051 | 1.0 | 0.9907 |
74
+ | 42.8642 | 3.2882 | 1700 | 46.8788 | 1.0 | 0.9907 |
75
+ | 42.8642 | 3.4816 | 1800 | 45.5411 | 1.0 | 0.9907 |
76
+ | 42.8642 | 3.6750 | 1900 | 44.1516 | 1.0 | 0.9907 |
77
+ | 38.3378 | 3.8685 | 2000 | 42.6087 | 1.0 | 0.9907 |
78
+ | 38.3378 | 4.0619 | 2100 | 40.9815 | 1.0 | 0.9907 |
79
+ | 38.3378 | 4.2553 | 2200 | 39.2401 | 1.0 | 0.9907 |
80
+ | 38.3378 | 4.4487 | 2300 | 37.4022 | 1.0 | 0.9908 |
81
+ | 38.3378 | 4.6422 | 2400 | 35.4309 | 1.0 | 0.9907 |
82
+ | 31.9192 | 4.8356 | 2500 | 33.4175 | 1.0 | 0.9907 |
83
+ | 31.9192 | 5.0290 | 2600 | 31.2660 | 1.0 | 0.9907 |
84
+ | 31.9192 | 5.2224 | 2700 | 29.0147 | 1.0 | 0.9908 |
85
+ | 31.9192 | 5.4159 | 2800 | 26.6885 | 1.0 | 0.9907 |
86
+ | 31.9192 | 5.6093 | 2900 | 24.3010 | 1.0 | 0.9907 |
87
+ | 23.4284 | 5.8027 | 3000 | 21.8808 | 1.0 | 0.9907 |
88
+ | 23.4284 | 5.9961 | 3100 | 19.4735 | 1.0 | 0.9908 |
89
+ | 23.4284 | 6.1896 | 3200 | 17.1293 | 1.0 | 0.9909 |
90
+ | 23.4284 | 6.3830 | 3300 | 14.8638 | 1.0 | 0.9908 |
91
+ | 23.4284 | 6.5764 | 3400 | 12.8062 | 1.0 | 0.9907 |
92
+ | 13.9431 | 6.7698 | 3500 | 10.9643 | 1.0 | 0.9907 |
93
+ | 13.9431 | 6.9632 | 3600 | 9.4119 | 1.0 | 0.9907 |
94
+ | 13.9431 | 7.1567 | 3700 | 8.1640 | 1.0 | 0.9907 |
95
+ | 13.9431 | 7.3501 | 3800 | 7.2297 | 1.0 | 0.9907 |
96
+ | 13.9431 | 7.5435 | 3900 | 6.5716 | 1.0 | 0.9907 |
97
+ | 7.4585 | 7.7369 | 4000 | 6.1413 | 1.0 | 0.9907 |
98
+ | 7.4585 | 7.9304 | 4100 | 5.8854 | 1.0 | 0.9907 |
99
+ | 7.4585 | 8.1238 | 4200 | 5.7707 | 1.0 | 0.9907 |
100
+ | 7.4585 | 8.3172 | 4300 | 5.6802 | 1.0 | 0.9907 |
101
+ | 7.4585 | 8.5106 | 4400 | 5.5971 | 1.0 | 0.9907 |
102
+ | 5.7398 | 8.7041 | 4500 | 5.5333 | 1.0 | 0.9907 |
103
+ | 5.7398 | 8.8975 | 4600 | 5.4751 | 1.0 | 0.9907 |
104
+ | 5.7398 | 9.0909 | 4700 | 5.4254 | 1.0 | 0.9907 |
105
+ | 5.7398 | 9.2843 | 4800 | 5.3775 | 1.1319 | 0.9908 |
106
+ | 5.7398 | 9.4778 | 4900 | 5.3433 | 1.3321 | 0.9907 |
107
+ | 5.4159 | 9.6712 | 5000 | 5.3119 | 1.6862 | 0.9906 |
108
+ | 5.4159 | 9.8646 | 5100 | 5.2691 | 1.4255 | 0.9910 |
109
+ | 5.4159 | 10.0580 | 5200 | 5.2369 | 1.4043 | 0.9909 |
110
+ | 5.4159 | 10.2515 | 5300 | 5.1949 | 1.5686 | 0.9910 |
111
+ | 5.4159 | 10.4449 | 5400 | 5.1519 | 1.5166 | 0.9908 |
112
+ | 5.2163 | 10.6383 | 5500 | 5.1081 | 1.2477 | 0.9910 |
113
+ | 5.2163 | 10.8317 | 5600 | 5.0553 | 1.5124 | 0.9908 |
114
+ | 5.2163 | 11.0251 | 5700 | 5.0123 | 1.5496 | 0.9909 |
115
+ | 5.2163 | 11.2186 | 5800 | 4.9424 | 1.7622 | 0.9886 |
116
+ | 5.2163 | 11.4120 | 5900 | 4.8753 | 1.5404 | 0.9831 |
117
+ | 4.9465 | 11.6054 | 6000 | 4.7768 | 1.8535 | 0.9750 |
118
+ | 4.9465 | 11.7988 | 6100 | 4.6841 | 1.8396 | 0.9713 |
119
+ | 4.9465 | 11.9923 | 6200 | 4.5828 | 1.7444 | 0.9697 |
120
+ | 4.9465 | 12.1857 | 6300 | 4.4853 | 1.8013 | 0.9689 |
121
+ | 4.9465 | 12.3791 | 6400 | 4.3955 | 1.8278 | 0.9556 |
122
+ | 4.5094 | 12.5725 | 6500 | 4.2842 | 1.8729 | 0.9123 |
123
+ | 4.5094 | 12.7660 | 6600 | 4.1819 | 1.9094 | 0.8650 |
124
+ | 4.5094 | 12.9594 | 6700 | 4.0741 | 1.9135 | 0.8486 |
125
+ | 4.5094 | 13.1528 | 6800 | 3.9649 | 1.9191 | 0.8386 |
126
+ | 4.5094 | 13.3462 | 6900 | 3.8641 | 1.9195 | 0.8189 |
127
+ | 4.0097 | 13.5397 | 7000 | 3.7687 | 1.9276 | 0.8014 |
128
+ | 4.0097 | 13.7331 | 7100 | 3.6808 | 1.9259 | 0.7963 |
129
+ | 4.0097 | 13.9265 | 7200 | 3.6021 | 1.9276 | 0.7792 |
130
+ | 4.0097 | 14.1199 | 7300 | 3.5533 | 1.9367 | 0.7775 |
131
+ | 4.0097 | 14.3133 | 7400 | 3.4768 | 1.9321 | 0.7751 |
132
+ | 3.5619 | 14.5068 | 7500 | 3.4285 | 1.9385 | 0.7672 |
133
+ | 3.5619 | 14.7002 | 7600 | 3.3628 | 1.9362 | 0.7660 |
134
+ | 3.5619 | 14.8936 | 7700 | 3.2910 | 1.9314 | 0.7619 |
135
+ | 3.5619 | 15.0870 | 7800 | 3.2243 | 1.9288 | 0.7486 |
136
+ | 3.5619 | 15.2805 | 7900 | 3.1645 | 1.9308 | 0.7432 |
137
+ | 3.2379 | 15.4739 | 8000 | 3.1186 | 1.9332 | 0.7383 |
138
+ | 3.2379 | 15.6673 | 8100 | 3.0783 | 1.9349 | 0.7375 |
139
+ | 3.2379 | 15.8607 | 8200 | 3.0146 | 1.9321 | 0.7279 |
140
+ | 3.2379 | 16.0542 | 8300 | 2.9523 | 1.9308 | 0.7300 |
141
+ | 3.2379 | 16.2476 | 8400 | 2.9187 | 1.9274 | 0.7254 |
142
+ | 2.9448 | 16.4410 | 8500 | 2.8671 | 1.9290 | 0.7177 |
143
+ | 2.9448 | 16.6344 | 8600 | 2.8189 | 1.9349 | 0.7116 |
144
+ | 2.9448 | 16.8279 | 8700 | 2.7691 | 1.9365 | 0.7078 |
145
+ | 2.9448 | 17.0213 | 8800 | 2.7317 | 1.9420 | 0.7069 |
146
+ | 2.9448 | 17.2147 | 8900 | 2.6832 | 1.9490 | 0.7056 |
147
+ | 2.6749 | 17.4081 | 9000 | 2.6420 | 1.9784 | 0.7020 |
148
+ | 2.6749 | 17.6015 | 9100 | 2.6020 | 1.9415 | 0.6991 |
149
+ | 2.6749 | 17.7950 | 9200 | 2.5667 | 1.9762 | 0.6995 |
150
+ | 2.6749 | 17.9884 | 9300 | 2.5171 | 1.9857 | 0.6771 |
151
+ | 2.6749 | 18.1818 | 9400 | 2.4922 | 1.9890 | 0.6775 |
152
+ | 2.4473 | 18.3752 | 9500 | 2.4455 | 1.9883 | 0.6683 |
153
+ | 2.4473 | 18.5687 | 9600 | 2.4192 | 1.9815 | 0.6621 |
154
+ | 2.4473 | 18.7621 | 9700 | 2.3866 | 1.9905 | 0.6523 |
155
+ | 2.4473 | 18.9555 | 9800 | 2.3354 | 1.9914 | 0.6539 |
156
+ | 2.4473 | 19.1489 | 9900 | 2.3114 | 1.9925 | 0.6516 |
157
+ | 2.2307 | 19.3424 | 10000 | 2.2695 | 1.9903 | 0.6454 |
158
+ | 2.2307 | 19.5358 | 10100 | 2.2466 | 1.9925 | 0.6464 |
159
+ | 2.2307 | 19.7292 | 10200 | 2.2167 | 1.9929 | 0.6423 |
160
+ | 2.2307 | 19.9226 | 10300 | 2.1762 | 1.9914 | 0.6413 |
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