Hugging Face's logo

slplab
/
apac_5sents_XLS-R_2_e-4

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
1
slplab commited on
Commit
6d8e114
·
1 Parent(s): 4609630

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +162 -0
README.md ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: apac_5sents_XLS-R_2_e-4
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # apac_5sents_XLS-R_2_e-4
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.4066
20
+ - Wer: 0.2188
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 32
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 128
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - training_steps: 20000
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
55
+ | 194.7445 | 11.11 | 200 | 81.6865 | 1.0 |
56
+ | 61.9115 | 22.22 | 400 | 39.3596 | 1.0 |
57
+ | 22.518 | 33.32 | 600 | 9.0332 | 1.0 |
58
+ | 6.0776 | 44.43 | 800 | 5.0634 | 1.0 |
59
+ | 4.555 | 55.54 | 1000 | 4.1552 | 1.0 |
60
+ | 2.402 | 66.65 | 1200 | 2.1760 | 0.7746 |
61
+ | 0.8349 | 77.76 | 1400 | 2.0442 | 0.8326 |
62
+ | 0.5484 | 88.86 | 1600 | 1.4219 | 0.8415 |
63
+ | 0.4242 | 99.97 | 1800 | 3.1197 | 0.8817 |
64
+ | 0.3173 | 111.11 | 2000 | 1.7508 | 0.7388 |
65
+ | 0.1989 | 122.22 | 2200 | 2.4075 | 0.6920 |
66
+ | 0.1169 | 133.32 | 2400 | 6.3769 | 0.5670 |
67
+ | 0.0925 | 144.43 | 2600 | 1.6440 | 0.4710 |
68
+ | 0.0681 | 155.54 | 2800 | 1.4864 | 0.3103 |
69
+ | 0.0561 | 166.65 | 3000 | 2.2973 | 0.3996 |
70
+ | 0.0445 | 177.76 | 3200 | 1.8107 | 0.4219 |
71
+ | 0.0336 | 188.86 | 3400 | 1.3867 | 0.3728 |
72
+ | 0.0344 | 199.97 | 3600 | 1.7830 | 0.3281 |
73
+ | 0.0345 | 211.11 | 3800 | 2.3773 | 0.3638 |
74
+ | 0.0304 | 222.22 | 4000 | 1.4448 | 0.1987 |
75
+ | 0.0357 | 233.32 | 4200 | 2.5893 | 0.3125 |
76
+ | 0.0253 | 244.43 | 4400 | 2.4619 | 0.3013 |
77
+ | 0.0212 | 255.54 | 4600 | 2.8144 | 0.2790 |
78
+ | 0.0186 | 266.65 | 4800 | 2.1155 | 0.2545 |
79
+ | 0.0196 | 277.76 | 5000 | 1.7306 | 0.2254 |
80
+ | 0.0153 | 288.86 | 5200 | 1.6247 | 0.2121 |
81
+ | 0.0146 | 299.97 | 5400 | 3.0580 | 0.4442 |
82
+ | 0.0296 | 311.11 | 5600 | 1.7865 | 0.2857 |
83
+ | 0.017 | 322.22 | 5800 | 5.4352 | 0.3795 |
84
+ | 0.0162 | 333.32 | 6000 | 1.9186 | 0.25 |
85
+ | 0.0139 | 344.43 | 6200 | 2.6566 | 0.2589 |
86
+ | 0.0139 | 355.54 | 6400 | 2.6532 | 0.2946 |
87
+ | 0.0111 | 366.65 | 6600 | 1.9131 | 0.2567 |
88
+ | 0.0119 | 377.76 | 6800 | 1.8914 | 0.3214 |
89
+ | 0.012 | 388.86 | 7000 | 2.2985 | 0.3371 |
90
+ | 0.0117 | 399.97 | 7200 | 3.3127 | 0.3393 |
91
+ | 0.0185 | 411.11 | 7400 | 3.1641 | 0.3862 |
92
+ | 0.0096 | 422.22 | 7600 | 2.3704 | 0.3973 |
93
+ | 0.007 | 433.32 | 7800 | 5.5839 | 0.4375 |
94
+ | 0.0104 | 444.43 | 8000 | 3.1441 | 0.3973 |
95
+ | 0.0098 | 455.54 | 8200 | 1.8188 | 0.2768 |
96
+ | 0.009 | 466.65 | 8400 | 1.8589 | 0.3058 |
97
+ | 0.0142 | 477.76 | 8600 | 3.9817 | 0.3772 |
98
+ | 0.0095 | 488.86 | 8800 | 2.1353 | 0.3237 |
99
+ | 0.0071 | 499.97 | 9000 | 1.5266 | 0.2902 |
100
+ | 0.0071 | 511.11 | 9200 | 1.4713 | 0.2746 |
101
+ | 0.0068 | 522.22 | 9400 | 2.2041 | 0.3125 |
102
+ | 0.0046 | 533.32 | 9600 | 1.4471 | 0.2522 |
103
+ | 0.0078 | 544.43 | 9800 | 1.6511 | 0.2946 |
104
+ | 0.0077 | 555.54 | 10000 | 1.7329 | 0.2121 |
105
+ | 0.004 | 566.65 | 10200 | 1.8652 | 0.2031 |
106
+ | 0.0049 | 577.76 | 10400 | 1.3661 | 0.2210 |
107
+ | 0.0066 | 588.86 | 10600 | 1.7544 | 0.2321 |
108
+ | 0.0072 | 599.97 | 10800 | 1.8081 | 0.2835 |
109
+ | 0.0055 | 611.11 | 11000 | 1.5139 | 0.2232 |
110
+ | 0.0053 | 622.22 | 11200 | 1.6138 | 0.2991 |
111
+ | 0.0052 | 633.32 | 11400 | 1.4865 | 0.2924 |
112
+ | 0.0067 | 644.43 | 11600 | 2.4807 | 0.3705 |
113
+ | 0.0044 | 655.54 | 11800 | 1.4097 | 0.3371 |
114
+ | 0.0026 | 666.65 | 12000 | 1.5313 | 0.3348 |
115
+ | 0.0055 | 677.76 | 12200 | 2.1968 | 0.3661 |
116
+ | 0.0034 | 688.86 | 12400 | 1.5198 | 0.3839 |
117
+ | 0.0028 | 699.97 | 12600 | 1.5379 | 0.3683 |
118
+ | 0.0033 | 711.11 | 12800 | 2.1355 | 0.3571 |
119
+ | 0.0044 | 722.22 | 13000 | 1.4440 | 0.3371 |
120
+ | 0.0024 | 733.32 | 13200 | 3.5154 | 0.3438 |
121
+ | 0.0012 | 744.43 | 13400 | 2.8505 | 0.3214 |
122
+ | 0.002 | 755.54 | 13600 | 2.9340 | 0.3304 |
123
+ | 0.0029 | 766.65 | 13800 | 2.8148 | 0.3214 |
124
+ | 0.0034 | 777.76 | 14000 | 2.7587 | 0.2835 |
125
+ | 0.0025 | 788.86 | 14200 | 2.8232 | 0.3638 |
126
+ | 0.0012 | 799.97 | 14400 | 2.6047 | 0.375 |
127
+ | 0.0015 | 811.11 | 14600 | 2.6364 | 0.3772 |
128
+ | 0.0018 | 822.22 | 14800 | 2.5143 | 0.3929 |
129
+ | 0.0032 | 833.32 | 15000 | 2.9826 | 0.5469 |
130
+ | 0.0035 | 844.43 | 15200 | 1.5761 | 0.4420 |
131
+ | 0.0023 | 855.54 | 15400 | 1.7465 | 0.4598 |
132
+ | 0.0016 | 866.65 | 15600 | 1.7740 | 0.4397 |
133
+ | 0.0007 | 877.76 | 15800 | 1.8296 | 0.4286 |
134
+ | 0.0012 | 888.86 | 16000 | 2.2368 | 0.3906 |
135
+ | 0.0027 | 899.97 | 16200 | 1.7112 | 0.3527 |
136
+ | 0.0009 | 911.11 | 16400 | 2.5084 | 0.375 |
137
+ | 0.001 | 922.22 | 16600 | 2.3311 | 0.3304 |
138
+ | 0.0019 | 933.32 | 16800 | 1.6653 | 0.3080 |
139
+ | 0.0018 | 944.43 | 17000 | 1.4620 | 0.2768 |
140
+ | 0.0007 | 955.54 | 17200 | 1.8509 | 0.2723 |
141
+ | 0.0005 | 966.65 | 17400 | 1.9279 | 0.2879 |
142
+ | 0.0009 | 977.76 | 17600 | 2.3558 | 0.2812 |
143
+ | 0.0004 | 988.86 | 17800 | 2.8907 | 0.2924 |
144
+ | 0.0011 | 999.97 | 18000 | 2.4847 | 0.2902 |
145
+ | 0.0016 | 1011.11 | 18200 | 2.2670 | 0.3058 |
146
+ | 0.0004 | 1022.22 | 18400 | 2.2399 | 0.3125 |
147
+ | 0.0004 | 1033.32 | 18600 | 2.4376 | 0.3192 |
148
+ | 0.001 | 1044.43 | 18800 | 2.4744 | 0.3214 |
149
+ | 0.0006 | 1055.54 | 19000 | 2.4975 | 0.3147 |
150
+ | 0.0006 | 1066.65 | 19200 | 2.6372 | 0.3259 |
151
+ | 0.0005 | 1077.76 | 19400 | 2.5817 | 0.3304 |
152
+ | 0.0004 | 1088.86 | 19600 | 2.5573 | 0.3326 |
153
+ | 0.0001 | 1099.97 | 19800 | 2.5579 | 0.3348 |
154
+ | 0.0003 | 1111.11 | 20000 | 2.5641 | 0.3326 |
155
+
156
+
157
+ ### Framework versions
158
+
159
+ - Transformers 4.26.1
160
+ - Pytorch 2.0.1+cu118
161
+ - Datasets 2.11.0
162
+ - Tokenizers 0.13.3