Hugging Face's logo

utakumi
/
Hubert-noisy_common_voice_debug

Automatic Speech Recognition
Transformers
Safetensors
Japanese
hubert
original_noisy_common_voice
Generated from Trainer
Inference Endpoints
Model card Files Community
utakumi commited on
Commit
df97da6
•
1 Parent(s): 0fc14b4

Model save

Browse files
Files changed (2) hide show
  1. README.md +177 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-noisy_common_voice_debug
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-noisy_common_voice_debug
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: 0.9670
22
+ - Wer: 1.0
23
+ - Cer: 0.3173
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: 0.0003
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: 30.0
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
58
+ | No log | 0.2660 | 100 | 12.0822 | 1.1570 | 1.0539 |
59
+ | No log | 0.5319 | 200 | 5.8789 | 1.0 | 0.9817 |
60
+ | No log | 0.7979 | 300 | 5.3627 | 1.0 | 0.9817 |
61
+ | No log | 1.0638 | 400 | 4.9316 | 1.0 | 0.9817 |
62
+ | 6.372 | 1.3298 | 500 | 4.4556 | 1.0 | 0.9817 |
63
+ | 6.372 | 1.5957 | 600 | 3.9890 | 1.0 | 0.9817 |
64
+ | 6.372 | 1.8617 | 700 | 3.5734 | 1.0 | 0.9817 |
65
+ | 6.372 | 2.1277 | 800 | 3.2932 | 1.0 | 0.9817 |
66
+ | 6.372 | 2.3936 | 900 | 3.1536 | 1.0 | 0.9817 |
67
+ | 3.4101 | 2.6596 | 1000 | 3.0484 | 1.0 | 0.9817 |
68
+ | 3.4101 | 2.9255 | 1100 | 2.8470 | 1.0 | 0.9808 |
69
+ | 3.4101 | 3.1915 | 1200 | 2.5211 | 1.0 | 0.8702 |
70
+ | 3.4101 | 3.4574 | 1300 | 2.0354 | 1.0 | 0.5518 |
71
+ | 3.4101 | 3.7234 | 1400 | 1.6780 | 1.0 | 0.4414 |
72
+ | 2.3222 | 3.9894 | 1500 | 1.5039 | 1.0 | 0.4312 |
73
+ | 2.3222 | 4.2553 | 1600 | 1.3419 | 1.0 | 0.3965 |
74
+ | 2.3222 | 4.5213 | 1700 | 1.2054 | 1.0 | 0.3686 |
75
+ | 2.3222 | 4.7872 | 1800 | 1.0588 | 1.0 | 0.3321 |
76
+ | 2.3222 | 5.0532 | 1900 | 0.9546 | 1.0 | 0.3158 |
77
+ | 1.2343 | 5.3191 | 2000 | 0.9042 | 1.0 | 0.3106 |
78
+ | 1.2343 | 5.5851 | 2100 | 0.8747 | 1.0 | 0.3088 |
79
+ | 1.2343 | 5.8511 | 2200 | 0.8224 | 1.0 | 0.2972 |
80
+ | 1.2343 | 6.1170 | 2300 | 0.8101 | 1.0 | 0.2996 |
81
+ | 1.2343 | 6.3830 | 2400 | 0.7892 | 1.0 | 0.2970 |
82
+ | 0.8716 | 6.6489 | 2500 | 0.7661 | 1.0 | 0.2915 |
83
+ | 0.8716 | 6.9149 | 2600 | 0.7654 | 1.0 | 0.2886 |
84
+ | 0.8716 | 7.1809 | 2700 | 0.7677 | 1.0 | 0.2898 |
85
+ | 0.8716 | 7.4468 | 2800 | 0.7528 | 1.0 | 0.2861 |
86
+ | 0.8716 | 7.7128 | 2900 | 0.7433 | 1.0 | 0.2880 |
87
+ | 0.7324 | 7.9787 | 3000 | 0.7498 | 1.0 | 0.2877 |
88
+ | 0.7324 | 8.2447 | 3100 | 0.7267 | 1.0 | 0.2827 |
89
+ | 0.7324 | 8.5106 | 3200 | 0.7319 | 1.0 | 0.2813 |
90
+ | 0.7324 | 8.7766 | 3300 | 0.7478 | 1.0 | 0.2882 |
91
+ | 0.7324 | 9.0426 | 3400 | 0.7337 | 1.0 | 0.2815 |
92
+ | 0.6486 | 9.3085 | 3500 | 0.7341 | 1.0 | 0.2851 |
93
+ | 0.6486 | 9.5745 | 3600 | 0.7419 | 1.0 | 0.2803 |
94
+ | 0.6486 | 9.8404 | 3700 | 0.7033 | 0.9998 | 0.2773 |
95
+ | 0.6486 | 10.1064 | 3800 | 0.7327 | 1.0 | 0.2829 |
96
+ | 0.6486 | 10.3723 | 3900 | 0.7554 | 0.9998 | 0.2855 |
97
+ | 0.6034 | 10.6383 | 4000 | 0.7361 | 1.0 | 0.2841 |
98
+ | 0.6034 | 10.9043 | 4100 | 0.7459 | 1.0 | 0.2833 |
99
+ | 0.6034 | 11.1702 | 4200 | 0.7384 | 1.0 | 0.2801 |
100
+ | 0.6034 | 11.4362 | 4300 | 0.7337 | 1.0 | 0.2776 |
101
+ | 0.6034 | 11.7021 | 4400 | 0.7572 | 1.0 | 0.2819 |
102
+ | 0.5687 | 11.9681 | 4500 | 0.7522 | 1.0 | 0.2824 |
103
+ | 0.5687 | 12.2340 | 4600 | 0.7491 | 1.0 | 0.2789 |
104
+ | 0.5687 | 12.5 | 4700 | 0.7485 | 1.0 | 0.2832 |
105
+ | 0.5687 | 12.7660 | 4800 | 0.7623 | 1.0 | 0.2849 |
106
+ | 0.5687 | 13.0319 | 4900 | 0.7829 | 1.0 | 0.2859 |
107
+ | 0.5255 | 13.2979 | 5000 | 0.7819 | 1.0 | 0.2820 |
108
+ | 0.5255 | 13.5638 | 5100 | 0.7783 | 0.9998 | 0.2824 |
109
+ | 0.5255 | 13.8298 | 5200 | 0.7653 | 1.0 | 0.2840 |
110
+ | 0.5255 | 14.0957 | 5300 | 0.7816 | 1.0 | 0.2822 |
111
+ | 0.5255 | 14.3617 | 5400 | 0.7608 | 1.0 | 0.2824 |
112
+ | 0.5016 | 14.6277 | 5500 | 0.7712 | 0.9998 | 0.2841 |
113
+ | 0.5016 | 14.8936 | 5600 | 0.7712 | 1.0 | 0.2864 |
114
+ | 0.5016 | 15.1596 | 5700 | 0.8153 | 0.9996 | 0.2851 |
115
+ | 0.5016 | 15.4255 | 5800 | 0.8161 | 0.9998 | 0.2852 |
116
+ | 0.5016 | 15.6915 | 5900 | 0.7911 | 1.0 | 0.2883 |
117
+ | 0.4821 | 15.9574 | 6000 | 0.7926 | 1.0 | 0.2823 |
118
+ | 0.4821 | 16.2234 | 6100 | 0.8147 | 1.0 | 0.2867 |
119
+ | 0.4821 | 16.4894 | 6200 | 0.7700 | 1.0 | 0.2826 |
120
+ | 0.4821 | 16.7553 | 6300 | 0.8119 | 1.0 | 0.2910 |
121
+ | 0.4821 | 17.0213 | 6400 | 0.8355 | 1.0 | 0.2846 |
122
+ | 0.4503 | 17.2872 | 6500 | 0.7936 | 0.9998 | 0.2859 |
123
+ | 0.4503 | 17.5532 | 6600 | 0.7976 | 0.9998 | 0.2952 |
124
+ | 0.4503 | 17.8191 | 6700 | 0.8274 | 0.9998 | 0.2902 |
125
+ | 0.4503 | 18.0851 | 6800 | 0.9034 | 0.9998 | 0.2885 |
126
+ | 0.4503 | 18.3511 | 6900 | 0.8066 | 0.9998 | 0.2882 |
127
+ | 0.4435 | 18.6170 | 7000 | 0.8495 | 1.0 | 0.2921 |
128
+ | 0.4435 | 18.8830 | 7100 | 0.8448 | 0.9998 | 0.2896 |
129
+ | 0.4435 | 19.1489 | 7200 | 0.8774 | 1.0 | 0.2904 |
130
+ | 0.4435 | 19.4149 | 7300 | 0.8293 | 0.9998 | 0.2973 |
131
+ | 0.4435 | 19.6809 | 7400 | 0.8038 | 1.0 | 0.2925 |
132
+ | 0.4457 | 19.9468 | 7500 | 0.8062 | 0.9998 | 0.2908 |
133
+ | 0.4457 | 20.2128 | 7600 | 0.8740 | 1.0 | 0.2918 |
134
+ | 0.4457 | 20.4787 | 7700 | 0.8489 | 1.0 | 0.2977 |
135
+ | 0.4457 | 20.7447 | 7800 | 0.8606 | 1.0 | 0.2973 |
136
+ | 0.4457 | 21.0106 | 7900 | 0.8141 | 0.9998 | 0.2926 |
137
+ | 0.4252 | 21.2766 | 8000 | 0.8832 | 0.9998 | 0.2984 |
138
+ | 0.4252 | 21.5426 | 8100 | 0.8590 | 0.9998 | 0.2945 |
139
+ | 0.4252 | 21.8085 | 8200 | 0.8304 | 0.9998 | 0.2940 |
140
+ | 0.4252 | 22.0745 | 8300 | 0.8734 | 0.9998 | 0.2974 |
141
+ | 0.4252 | 22.3404 | 8400 | 0.8417 | 0.9998 | 0.2930 |
142
+ | 0.418 | 22.6064 | 8500 | 0.9387 | 1.0 | 0.2993 |
143
+ | 0.418 | 22.8723 | 8600 | 0.8810 | 1.0 | 0.2996 |
144
+ | 0.418 | 23.1383 | 8700 | 0.9090 | 1.0 | 0.3074 |
145
+ | 0.418 | 23.4043 | 8800 | 0.8993 | 0.9998 | 0.3107 |
146
+ | 0.418 | 23.6702 | 8900 | 0.8724 | 1.0 | 0.3033 |
147
+ | 0.424 | 23.9362 | 9000 | 0.8895 | 0.9998 | 0.3042 |
148
+ | 0.424 | 24.2021 | 9100 | 0.8863 | 1.0 | 0.3014 |
149
+ | 0.424 | 24.4681 | 9200 | 0.9255 | 0.9998 | 0.3112 |
150
+ | 0.424 | 24.7340 | 9300 | 0.9398 | 0.9998 | 0.3011 |
151
+ | 0.424 | 25.0 | 9400 | 0.8763 | 0.9998 | 0.3071 |
152
+ | 0.4122 | 25.2660 | 9500 | 0.9353 | 1.0 | 0.3090 |
153
+ | 0.4122 | 25.5319 | 9600 | 0.9382 | 1.0 | 0.3128 |
154
+ | 0.4122 | 25.7979 | 9700 | 0.9295 | 0.9998 | 0.3102 |
155
+ | 0.4122 | 26.0638 | 9800 | 0.9286 | 0.9998 | 0.3092 |
156
+ | 0.4122 | 26.3298 | 9900 | 0.9141 | 1.0 | 0.3014 |
157
+ | 0.4146 | 26.5957 | 10000 | 0.9426 | 1.0 | 0.3126 |
158
+ | 0.4146 | 26.8617 | 10100 | 0.8652 | 1.0 | 0.3032 |
159
+ | 0.4146 | 27.1277 | 10200 | 0.9289 | 1.0 | 0.3105 |
160
+ | 0.4146 | 27.3936 | 10300 | 0.9459 | 1.0 | 0.3103 |
161
+ | 0.4146 | 27.6596 | 10400 | 0.9137 | 0.9998 | 0.3124 |
162
+ | 0.416 | 27.9255 | 10500 | 0.9305 | 1.0 | 0.3100 |
163
+ | 0.416 | 28.1915 | 10600 | 0.9589 | 1.0 | 0.3071 |
164
+ | 0.416 | 28.4574 | 10700 | 0.9276 | 0.9998 | 0.3061 |
165
+ | 0.416 | 28.7234 | 10800 | 0.9259 | 1.0 | 0.3078 |
166
+ | 0.416 | 28.9894 | 10900 | 0.9287 | 1.0 | 0.3150 |
167
+ | 0.4078 | 29.2553 | 11000 | 0.9346 | 0.9998 | 0.3166 |
168
+ | 0.4078 | 29.5213 | 11100 | 0.9559 | 1.0 | 0.3165 |
169
+ | 0.4078 | 29.7872 | 11200 | 0.9670 | 1.0 | 0.3173 |
170
+
171
+
172
+ ### Framework versions
173
+
174
+ - Transformers 4.47.0.dev0
175
+ - Pytorch 2.5.1+cu124
176
+ - Datasets 3.1.0
177
+ - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec1c3fa34d5e2ace1714f444cafa1678d97d9f05d633ed2598958c2e8210a66a
3
  size 377647624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b202dfb06c29c84670c079890f402ad58628ae47de7879942dd16cf0348731f5
3
  size 377647624