Hugging Face's logo

utakumi
/
Hubert-common_voice-phoneme-ctc_zero_infinity

Automatic Speech Recognition
Transformers
Safetensors
Japanese
hubert
mozilla-foundation/common_voice_13_0
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
utakumi commited on
Commit
89f6b54
·
verified ·
1 Parent(s): 6447199

Model save

Browse files
Files changed (1) hide show
  1. README.md +155 -0
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-phoneme-ctc_zero_infinity
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-phoneme-ctc_zero_infinity
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: 0.5488
37
+ - Wer: 1.0
38
+ - Cer: 0.1977
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: 20.0
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 | 18.2381 | 1.1471 | 1.8153 |
74
+ | No log | 0.5319 | 200 | 8.1726 | 1.0 | 0.9817 |
75
+ | No log | 0.7979 | 300 | 6.9386 | 1.0 | 0.9817 |
76
+ | No log | 1.0638 | 400 | 6.2389 | 1.0 | 0.9817 |
77
+ | 8.8178 | 1.3298 | 500 | 5.4653 | 1.0 | 0.9817 |
78
+ | 8.8178 | 1.5957 | 600 | 4.6745 | 1.0 | 0.9817 |
79
+ | 8.8178 | 1.8617 | 700 | 3.9771 | 1.0 | 0.9817 |
80
+ | 8.8178 | 2.1277 | 800 | 3.4579 | 1.0 | 0.9817 |
81
+ | 8.8178 | 2.3936 | 900 | 3.1745 | 1.0 | 0.9817 |
82
+ | 3.6858 | 2.6596 | 1000 | 3.0675 | 1.0 | 0.9817 |
83
+ | 3.6858 | 2.9255 | 1100 | 3.0343 | 1.0 | 0.9817 |
84
+ | 3.6858 | 3.1915 | 1200 | 3.0102 | 1.0 | 0.9817 |
85
+ | 3.6858 | 3.4574 | 1300 | 2.9925 | 1.0 | 0.9817 |
86
+ | 3.6858 | 3.7234 | 1400 | 2.5595 | 1.0 | 0.9367 |
87
+ | 2.7891 | 3.9894 | 1500 | 1.5432 | 1.0 | 0.3742 |
88
+ | 2.7891 | 4.2553 | 1600 | 1.0799 | 1.0 | 0.2972 |
89
+ | 2.7891 | 4.5213 | 1700 | 0.8670 | 1.0 | 0.2639 |
90
+ | 2.7891 | 4.7872 | 1800 | 0.7350 | 1.0 | 0.2559 |
91
+ | 2.7891 | 5.0532 | 1900 | 0.6753 | 1.0 | 0.2468 |
92
+ | 0.9179 | 5.3191 | 2000 | 0.6171 | 1.0 | 0.2389 |
93
+ | 0.9179 | 5.5851 | 2100 | 0.5866 | 1.0 | 0.2386 |
94
+ | 0.9179 | 5.8511 | 2200 | 0.5649 | 1.0 | 0.2389 |
95
+ | 0.9179 | 6.1170 | 2300 | 0.5368 | 1.0 | 0.2321 |
96
+ | 0.9179 | 6.3830 | 2400 | 0.5225 | 1.0 | 0.2289 |
97
+ | 0.563 | 6.6489 | 2500 | 0.5042 | 1.0 | 0.2293 |
98
+ | 0.563 | 6.9149 | 2600 | 0.4918 | 1.0 | 0.2247 |
99
+ | 0.563 | 7.1809 | 2700 | 0.4881 | 1.0 | 0.2208 |
100
+ | 0.563 | 7.4468 | 2800 | 0.4787 | 1.0 | 0.2198 |
101
+ | 0.563 | 7.7128 | 2900 | 0.4692 | 1.0 | 0.2181 |
102
+ | 0.4453 | 7.9787 | 3000 | 0.4733 | 1.0 | 0.2151 |
103
+ | 0.4453 | 8.2447 | 3100 | 0.4585 | 1.0 | 0.2147 |
104
+ | 0.4453 | 8.5106 | 3200 | 0.4463 | 1.0 | 0.2116 |
105
+ | 0.4453 | 8.7766 | 3300 | 0.4183 | 1.0 | 0.2055 |
106
+ | 0.4453 | 9.0426 | 3400 | 0.4308 | 0.9998 | 0.2032 |
107
+ | 0.3596 | 9.3085 | 3500 | 0.4070 | 1.0 | 0.2022 |
108
+ | 0.3596 | 9.5745 | 3600 | 0.4259 | 1.0 | 0.2024 |
109
+ | 0.3596 | 9.8404 | 3700 | 0.4038 | 1.0 | 0.1985 |
110
+ | 0.3596 | 10.1064 | 3800 | 0.4272 | 1.0 | 0.1976 |
111
+ | 0.3596 | 10.3723 | 3900 | 0.3961 | 0.9998 | 0.1969 |
112
+ | 0.2945 | 10.6383 | 4000 | 0.4180 | 1.0 | 0.1943 |
113
+ | 0.2945 | 10.9043 | 4100 | 0.3999 | 1.0 | 0.1975 |
114
+ | 0.2945 | 11.1702 | 4200 | 0.3879 | 1.0 | 0.1930 |
115
+ | 0.2945 | 11.4362 | 4300 | 0.3799 | 1.0 | 0.1918 |
116
+ | 0.2945 | 11.7021 | 4400 | 0.3764 | 0.9998 | 0.1927 |
117
+ | 0.2605 | 11.9681 | 4500 | 0.3725 | 1.0 | 0.1919 |
118
+ | 0.2605 | 12.2340 | 4600 | 0.3910 | 1.0 | 0.1919 |
119
+ | 0.2605 | 12.5 | 4700 | 0.3851 | 0.9996 | 0.1908 |
120
+ | 0.2605 | 12.7660 | 4800 | 0.4115 | 1.0 | 0.1906 |
121
+ | 0.2605 | 13.0319 | 4900 | 0.3779 | 1.0 | 0.1894 |
122
+ | 0.2223 | 13.2979 | 5000 | 0.3956 | 1.0 | 0.1904 |
123
+ | 0.2223 | 13.5638 | 5100 | 0.4001 | 1.0 | 0.1907 |
124
+ | 0.2223 | 13.8298 | 5200 | 0.3891 | 1.0 | 0.1948 |
125
+ | 0.2223 | 14.0957 | 5300 | 0.3940 | 1.0 | 0.1902 |
126
+ | 0.2223 | 14.3617 | 5400 | 0.4056 | 1.0 | 0.1909 |
127
+ | 0.211 | 14.6277 | 5500 | 0.4000 | 0.9998 | 0.1929 |
128
+ | 0.211 | 14.8936 | 5600 | 0.3926 | 1.0 | 0.1895 |
129
+ | 0.211 | 15.1596 | 5700 | 0.3852 | 0.9998 | 0.1930 |
130
+ | 0.211 | 15.4255 | 5800 | 0.3864 | 1.0 | 0.1886 |
131
+ | 0.211 | 15.6915 | 5900 | 0.3951 | 0.9998 | 0.1909 |
132
+ | 0.1983 | 15.9574 | 6000 | 0.3951 | 1.0 | 0.1882 |
133
+ | 0.1983 | 16.2234 | 6100 | 0.4087 | 1.0 | 0.1918 |
134
+ | 0.1983 | 16.4894 | 6200 | 0.4150 | 1.0 | 0.1891 |
135
+ | 0.1983 | 16.7553 | 6300 | 0.4008 | 0.9998 | 0.1907 |
136
+ | 0.1983 | 17.0213 | 6400 | 0.4220 | 1.0 | 0.1943 |
137
+ | 0.1829 | 17.2872 | 6500 | 0.4154 | 1.0 | 0.1925 |
138
+ | 0.1829 | 17.5532 | 6600 | 0.4482 | 1.0 | 0.1959 |
139
+ | 0.1829 | 17.8191 | 6700 | 0.4217 | 0.9998 | 0.1939 |
140
+ | 0.1829 | 18.0851 | 6800 | 0.4383 | 0.9998 | 0.1916 |
141
+ | 0.1829 | 18.3511 | 6900 | 0.4226 | 1.0 | 0.1926 |
142
+ | 0.1757 | 18.6170 | 7000 | 0.4170 | 0.9998 | 0.1916 |
143
+ | 0.1757 | 18.8830 | 7100 | 0.4162 | 1.0 | 0.1918 |
144
+ | 0.1757 | 19.1489 | 7200 | 0.4350 | 0.9998 | 0.1910 |
145
+ | 0.1757 | 19.4149 | 7300 | 0.4403 | 1.0 | 0.2022 |
146
+ | 0.1757 | 19.6809 | 7400 | 0.4325 | 0.9998 | 0.1944 |
147
+ | 0.1801 | 19.9468 | 7500 | 0.5488 | 1.0 | 0.1977 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.47.0.dev0
153
+ - Pytorch 2.5.1+cu124
154
+ - Datasets 3.1.0
155
+ - Tokenizers 0.20.3