Hugging Face's logo

utakumi
/
Hubert-common_voice-phonemes-debug

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
09a5e3c
·
verified ·
1 Parent(s): 321728c

Model save

Browse files
Files changed (1) hide show
  1. README.md +192 -0
README.md ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-phonemes-debug
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: 0.9944490702192618
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-phonemes-debug
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: 0.4527
37
+ - Wer: 0.9944
38
+ - Cer: 0.1933
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: cosine
65
+ - lr_scheduler_warmup_steps: 12500
66
+ - num_epochs: 30.0
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 | 18.5364 | 1.0645 | 1.8292 |
74
+ | No log | 0.5319 | 200 | 8.2791 | 1.0 | 0.9813 |
75
+ | No log | 0.7979 | 300 | 7.0224 | 1.0 | 0.9813 |
76
+ | No log | 1.0638 | 400 | 6.3106 | 1.0 | 0.9813 |
77
+ | 8.9892 | 1.3298 | 500 | 5.5223 | 1.0 | 0.9813 |
78
+ | 8.9892 | 1.5957 | 600 | 4.7121 | 1.0 | 0.9813 |
79
+ | 8.9892 | 1.8617 | 700 | 4.0028 | 1.0 | 0.9813 |
80
+ | 8.9892 | 2.1277 | 800 | 3.4755 | 1.0 | 0.9813 |
81
+ | 8.9892 | 2.3936 | 900 | 3.1988 | 1.0 | 0.9813 |
82
+ | 3.7187 | 2.6596 | 1000 | 3.0792 | 1.0 | 0.9813 |
83
+ | 3.7187 | 2.9255 | 1100 | 3.0459 | 1.0 | 0.9813 |
84
+ | 3.7187 | 3.1915 | 1200 | 3.0360 | 1.0 | 0.9813 |
85
+ | 3.7187 | 3.4574 | 1300 | 3.0084 | 1.0 | 0.9813 |
86
+ | 3.7187 | 3.7234 | 1400 | 2.4956 | 1.0 | 0.9343 |
87
+ | 2.783 | 3.9894 | 1500 | 1.4418 | 1.0 | 0.3331 |
88
+ | 2.783 | 4.2553 | 1600 | 1.0228 | 1.0 | 0.2753 |
89
+ | 2.783 | 4.5213 | 1700 | 0.8218 | 1.0 | 0.2532 |
90
+ | 2.783 | 4.7872 | 1800 | 0.7084 | 1.0 | 0.2433 |
91
+ | 2.783 | 5.0532 | 1900 | 0.6306 | 1.0 | 0.2337 |
92
+ | 0.8659 | 5.3191 | 2000 | 0.5934 | 1.0 | 0.2310 |
93
+ | 0.8659 | 5.5851 | 2100 | 0.5648 | 1.0 | 0.2284 |
94
+ | 0.8659 | 5.8511 | 2200 | 0.5330 | 1.0 | 0.2214 |
95
+ | 0.8659 | 6.1170 | 2300 | 0.5139 | 1.0 | 0.2209 |
96
+ | 0.8659 | 6.3830 | 2400 | 0.4907 | 1.0 | 0.2159 |
97
+ | 0.5271 | 6.6489 | 2500 | 0.4640 | 1.0 | 0.2160 |
98
+ | 0.5271 | 6.9149 | 2600 | 0.4609 | 1.0 | 0.2112 |
99
+ | 0.5271 | 7.1809 | 2700 | 0.4550 | 1.0001 | 0.2097 |
100
+ | 0.5271 | 7.4468 | 2800 | 0.4601 | 0.9992 | 0.2100 |
101
+ | 0.5271 | 7.7128 | 2900 | 0.4290 | 0.9953 | 0.2051 |
102
+ | 0.4244 | 7.9787 | 3000 | 0.4256 | 0.9971 | 0.2024 |
103
+ | 0.4244 | 8.2447 | 3100 | 0.4135 | 0.9999 | 0.2014 |
104
+ | 0.4244 | 8.5106 | 3200 | 0.4125 | 0.9956 | 0.1999 |
105
+ | 0.4244 | 8.7766 | 3300 | 0.3886 | 0.9942 | 0.1927 |
106
+ | 0.4244 | 9.0426 | 3400 | 0.3833 | 1.0006 | 0.1911 |
107
+ | 0.3373 | 9.3085 | 3500 | 0.3611 | 1.0364 | 0.1887 |
108
+ | 0.3373 | 9.5745 | 3600 | 0.3585 | 1.0080 | 0.1843 |
109
+ | 0.3373 | 9.8404 | 3700 | 0.3562 | 0.9981 | 0.1855 |
110
+ | 0.3373 | 10.1064 | 3800 | 0.3412 | 0.9883 | 0.1799 |
111
+ | 0.3373 | 10.3723 | 3900 | 0.3561 | 0.9835 | 0.1846 |
112
+ | 0.2779 | 10.6383 | 4000 | 0.3482 | 0.9772 | 0.1798 |
113
+ | 0.2779 | 10.9043 | 4100 | 0.3266 | 0.9795 | 0.1793 |
114
+ | 0.2779 | 11.1702 | 4200 | 0.3484 | 0.9792 | 0.1789 |
115
+ | 0.2779 | 11.4362 | 4300 | 0.3378 | 0.9992 | 0.1799 |
116
+ | 0.2779 | 11.7021 | 4400 | 0.3330 | 0.9764 | 0.1795 |
117
+ | 0.2409 | 11.9681 | 4500 | 0.3208 | 0.9781 | 0.1792 |
118
+ | 0.2409 | 12.2340 | 4600 | 0.3602 | 0.9757 | 0.1805 |
119
+ | 0.2409 | 12.5 | 4700 | 0.3363 | 0.9939 | 0.1788 |
120
+ | 0.2409 | 12.7660 | 4800 | 0.3253 | 0.9732 | 0.1795 |
121
+ | 0.2409 | 13.0319 | 4900 | 0.3285 | 0.9711 | 0.1762 |
122
+ | 0.2104 | 13.2979 | 5000 | 0.3233 | 0.9729 | 0.1769 |
123
+ | 0.2104 | 13.5638 | 5100 | 0.3363 | 0.9775 | 0.1827 |
124
+ | 0.2104 | 13.8298 | 5200 | 0.3371 | 0.9684 | 0.1759 |
125
+ | 0.2104 | 14.0957 | 5300 | 0.3464 | 0.9731 | 0.1778 |
126
+ | 0.2104 | 14.3617 | 5400 | 0.3450 | 0.9777 | 0.1783 |
127
+ | 0.1947 | 14.6277 | 5500 | 0.3442 | 0.9681 | 0.1773 |
128
+ | 0.1947 | 14.8936 | 5600 | 0.3346 | 0.9858 | 0.1780 |
129
+ | 0.1947 | 15.1596 | 5700 | 0.3524 | 0.9732 | 0.1771 |
130
+ | 0.1947 | 15.4255 | 5800 | 0.3414 | 0.9782 | 0.1774 |
131
+ | 0.1947 | 15.6915 | 5900 | 0.3438 | 1.0019 | 0.1766 |
132
+ | 0.1892 | 15.9574 | 6000 | 0.3391 | 0.9706 | 0.1802 |
133
+ | 0.1892 | 16.2234 | 6100 | 0.3505 | 0.9782 | 0.1803 |
134
+ | 0.1892 | 16.4894 | 6200 | 0.3467 | 0.9736 | 0.1767 |
135
+ | 0.1892 | 16.7553 | 6300 | 0.3681 | 0.9946 | 0.1792 |
136
+ | 0.1892 | 17.0213 | 6400 | 0.3557 | 1.0104 | 0.1769 |
137
+ | 0.1749 | 17.2872 | 6500 | 0.3446 | 0.9770 | 0.1787 |
138
+ | 0.1749 | 17.5532 | 6600 | 0.3496 | 0.9839 | 0.1803 |
139
+ | 0.1749 | 17.8191 | 6700 | 0.3585 | 1.0012 | 0.1806 |
140
+ | 0.1749 | 18.0851 | 6800 | 0.3562 | 0.9717 | 0.1799 |
141
+ | 0.1749 | 18.3511 | 6900 | 0.3722 | 1.0504 | 0.1835 |
142
+ | 0.1717 | 18.6170 | 7000 | 0.3554 | 0.9772 | 0.1809 |
143
+ | 0.1717 | 18.8830 | 7100 | 0.3678 | 0.9684 | 0.1788 |
144
+ | 0.1717 | 19.1489 | 7200 | 0.4938 | 1.0419 | 0.1854 |
145
+ | 0.1717 | 19.4149 | 7300 | 0.3926 | 0.9827 | 0.1805 |
146
+ | 0.1717 | 19.6809 | 7400 | 0.3581 | 1.0001 | 0.1819 |
147
+ | 0.1715 | 19.9468 | 7500 | 0.3569 | 0.9929 | 0.1840 |
148
+ | 0.1715 | 20.2128 | 7600 | 0.3911 | 0.9969 | 0.1814 |
149
+ | 0.1715 | 20.4787 | 7700 | 0.3973 | 1.0017 | 0.1808 |
150
+ | 0.1715 | 20.7447 | 7800 | 0.3943 | 0.9724 | 0.1839 |
151
+ | 0.1715 | 21.0106 | 7900 | 0.3984 | 0.9764 | 0.1823 |
152
+ | 0.1667 | 21.2766 | 8000 | 0.4306 | 1.0500 | 0.1840 |
153
+ | 0.1667 | 21.5426 | 8100 | 0.3794 | 0.9728 | 0.1882 |
154
+ | 0.1667 | 21.8085 | 8200 | 0.3966 | 0.9913 | 0.1834 |
155
+ | 0.1667 | 22.0745 | 8300 | 0.3981 | 0.9745 | 0.1838 |
156
+ | 0.1667 | 22.3404 | 8400 | 0.4328 | 0.9926 | 0.1826 |
157
+ | 0.1625 | 22.6064 | 8500 | 0.4087 | 0.9710 | 0.1835 |
158
+ | 0.1625 | 22.8723 | 8600 | 0.4149 | 1.0062 | 0.1861 |
159
+ | 0.1625 | 23.1383 | 8700 | 0.4107 | 0.9921 | 0.1875 |
160
+ | 0.1625 | 23.4043 | 8800 | 0.4140 | 0.9835 | 0.1869 |
161
+ | 0.1625 | 23.6702 | 8900 | 0.4087 | 0.9918 | 0.1890 |
162
+ | 0.1647 | 23.9362 | 9000 | 0.4083 | 0.9842 | 0.1870 |
163
+ | 0.1647 | 24.2021 | 9100 | 0.4006 | 0.9858 | 0.1847 |
164
+ | 0.1647 | 24.4681 | 9200 | 0.4137 | 1.0015 | 0.1850 |
165
+ | 0.1647 | 24.7340 | 9300 | 0.4107 | 0.9994 | 0.1906 |
166
+ | 0.1647 | 25.0 | 9400 | 0.4209 | 0.9843 | 0.1912 |
167
+ | 0.1667 | 25.2660 | 9500 | 0.4373 | 0.9957 | 0.1893 |
168
+ | 0.1667 | 25.5319 | 9600 | 0.4390 | 0.9822 | 0.1890 |
169
+ | 0.1667 | 25.7979 | 9700 | 0.4539 | 0.9857 | 0.1964 |
170
+ | 0.1667 | 26.0638 | 9800 | 0.4381 | 1.0037 | 0.1933 |
171
+ | 0.1667 | 26.3298 | 9900 | 0.4227 | 0.9875 | 0.1865 |
172
+ | 0.1644 | 26.5957 | 10000 | 0.4802 | 1.0266 | 0.1884 |
173
+ | 0.1644 | 26.8617 | 10100 | 0.4389 | 0.9950 | 0.1958 |
174
+ | 0.1644 | 27.1277 | 10200 | 0.4744 | 0.9828 | 0.1939 |
175
+ | 0.1644 | 27.3936 | 10300 | 0.4494 | 1.0006 | 0.1983 |
176
+ | 0.1644 | 27.6596 | 10400 | 0.4414 | 0.9963 | 0.1961 |
177
+ | 0.1742 | 27.9255 | 10500 | 0.4668 | 0.9764 | 0.1932 |
178
+ | 0.1742 | 28.1915 | 10600 | 0.4284 | 0.9720 | 0.1878 |
179
+ | 0.1742 | 28.4574 | 10700 | 0.4258 | 1.0279 | 0.1944 |
180
+ | 0.1742 | 28.7234 | 10800 | 0.4251 | 1.0024 | 0.1892 |
181
+ | 0.1742 | 28.9894 | 10900 | 0.4597 | 1.0201 | 0.1978 |
182
+ | 0.1669 | 29.2553 | 11000 | 0.4414 | 0.9879 | 0.1919 |
183
+ | 0.1669 | 29.5213 | 11100 | 0.4473 | 0.9772 | 0.1909 |
184
+ | 0.1669 | 29.7872 | 11200 | 0.4527 | 0.9944 | 0.1933 |
185
+
186
+
187
+ ### Framework versions
188
+
189
+ - Transformers 4.47.0.dev0
190
+ - Pytorch 2.5.1+cu124
191
+ - Datasets 3.1.0
192
+ - Tokenizers 0.20.3