Hugging Face's logo

slplab
/
apac_5sents_XLS-R_2_1e-6_10000

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
1
slplab commited on
Commit
d2f583e
·
1 Parent(s): 5d70904

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_1e-6_10000
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_1e-6_10000
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: 235.4551
20
+ - Wer: 1.0
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: 1e-06
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: 10000
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
55
+ | 283.4719 | 5.54 | 100 | 275.8542 | 1.1562 |
56
+ | 284.9797 | 11.11 | 200 | 275.2194 | 1.1317 |
57
+ | 281.7698 | 16.65 | 300 | 272.7092 | 1.0714 |
58
+ | 277.0381 | 22.22 | 400 | 262.7592 | 1.0022 |
59
+ | 255.1038 | 27.76 | 500 | 235.9033 | 1.0 |
60
+ | 210.0999 | 33.32 | 600 | 187.6442 | 1.0 |
61
+ | 165.675 | 38.86 | 700 | 147.7660 | 1.0 |
62
+ | 136.7341 | 44.43 | 800 | 119.9158 | 1.0 |
63
+ | 115.6304 | 49.97 | 900 | 103.3855 | 1.0 |
64
+ | 102.5195 | 55.54 | 1000 | 92.6710 | 1.0 |
65
+ | 92.8874 | 61.11 | 1100 | 85.5879 | 1.0 |
66
+ | 85.7572 | 66.65 | 1200 | 80.7715 | 1.0 |
67
+ | 82.2298 | 72.22 | 1300 | 77.2967 | 1.0 |
68
+ | 78.2917 | 77.76 | 1400 | 74.5786 | 1.0 |
69
+ | 76.1737 | 83.32 | 1500 | 72.3749 | 1.0 |
70
+ | 73.4032 | 88.86 | 1600 | 70.5145 | 1.0 |
71
+ | 72.0308 | 94.43 | 1700 | 68.8751 | 1.0 |
72
+ | 70.2158 | 99.97 | 1800 | 67.3867 | 1.0 |
73
+ | 69.0366 | 105.54 | 1900 | 66.0221 | 1.0 |
74
+ | 67.505 | 111.11 | 2000 | 64.7385 | 1.0 |
75
+ | 65.9735 | 116.65 | 2100 | 63.5326 | 1.0 |
76
+ | 64.9547 | 122.22 | 2200 | 62.3629 | 1.0 |
77
+ | 63.5495 | 127.76 | 2300 | 61.2392 | 1.0 |
78
+ | 62.5682 | 133.32 | 2400 | 60.1489 | 1.0 |
79
+ | 61.3491 | 138.86 | 2500 | 59.0903 | 1.0 |
80
+ | 60.4633 | 144.43 | 2600 | 58.0601 | 1.0 |
81
+ | 59.1225 | 149.97 | 2700 | 57.0598 | 1.0 |
82
+ | 58.4608 | 155.54 | 2800 | 56.0791 | 1.0 |
83
+ | 57.3886 | 161.11 | 2900 | 55.1206 | 1.0 |
84
+ | 56.0671 | 166.65 | 3000 | 54.1854 | 1.0 |
85
+ | 55.4618 | 172.22 | 3100 | 53.2703 | 1.0 |
86
+ | 54.3707 | 177.76 | 3200 | 52.3758 | 1.0 |
87
+ | 53.5913 | 183.32 | 3300 | 51.4962 | 1.0 |
88
+ | 52.3333 | 188.86 | 3400 | 50.6445 | 1.0 |
89
+ | 51.9007 | 194.43 | 3500 | 49.8066 | 1.0 |
90
+ | 50.7232 | 199.97 | 3600 | 48.9866 | 1.0 |
91
+ | 50.1234 | 205.54 | 3700 | 48.1893 | 1.0 |
92
+ | 49.3482 | 211.11 | 3800 | 47.4028 | 1.0 |
93
+ | 48.2667 | 216.65 | 3900 | 46.6400 | 1.0 |
94
+ | 47.6979 | 222.22 | 4000 | 45.8918 | 1.0 |
95
+ | 46.8316 | 227.76 | 4100 | 45.1604 | 1.0 |
96
+ | 46.2709 | 233.32 | 4200 | 44.4558 | 1.0 |
97
+ | 45.2221 | 238.86 | 4300 | 43.7601 | 1.0 |
98
+ | 44.7131 | 244.43 | 4400 | 43.0846 | 1.0 |
99
+ | 43.9629 | 249.97 | 4500 | 42.4227 | 1.0 |
100
+ | 43.4376 | 255.54 | 4600 | 41.7802 | 1.0 |
101
+ | 42.8012 | 261.11 | 4700 | 41.1533 | 1.0 |
102
+ | 41.963 | 266.65 | 4800 | 40.5411 | 1.0 |
103
+ | 41.5048 | 272.22 | 4900 | 39.9454 | 1.0 |
104
+ | 40.7667 | 277.76 | 5000 | 39.3722 | 1.0 |
105
+ | 40.3653 | 283.32 | 5100 | 38.8072 | 1.0 |
106
+ | 39.4755 | 288.86 | 5200 | 38.2610 | 1.0 |
107
+ | 39.2028 | 294.43 | 5300 | 37.7295 | 1.0 |
108
+ | 38.5202 | 299.97 | 5400 | 37.2128 | 1.0 |
109
+ | 38.1717 | 305.54 | 5500 | 36.7152 | 1.0 |
110
+ | 37.6775 | 311.11 | 5600 | 36.2277 | 1.0 |
111
+ | 36.9204 | 316.65 | 5700 | 35.7579 | 1.0 |
112
+ | 36.6353 | 322.22 | 5800 | 35.2993 | 1.0 |
113
+ | 36.0619 | 327.76 | 5900 | 34.8580 | 1.0 |
114
+ | 35.7494 | 333.32 | 6000 | 34.4316 | 1.0 |
115
+ | 35.0993 | 338.86 | 6100 | 34.0134 | 1.0 |
116
+ | 34.903 | 344.43 | 6200 | 33.6148 | 1.0 |
117
+ | 34.3435 | 349.97 | 6300 | 33.2321 | 1.0 |
118
+ | 34.1451 | 355.54 | 6400 | 32.8573 | 1.0 |
119
+ | 33.663 | 361.11 | 6500 | 32.4956 | 1.0 |
120
+ | 33.1929 | 366.65 | 6600 | 32.1511 | 1.0 |
121
+ | 32.9852 | 372.22 | 6700 | 31.8129 | 1.0 |
122
+ | 32.5427 | 377.76 | 6800 | 31.4935 | 1.0 |
123
+ | 32.3938 | 383.32 | 6900 | 31.1799 | 1.0 |
124
+ | 31.777 | 388.86 | 7000 | 30.8769 | 1.0 |
125
+ | 31.7616 | 394.43 | 7100 | 30.5909 | 1.0 |
126
+ | 31.2618 | 399.97 | 7200 | 30.3215 | 1.0 |
127
+ | 31.2144 | 405.54 | 7300 | 30.0532 | 1.0 |
128
+ | 30.8797 | 411.11 | 7400 | 29.8014 | 1.0 |
129
+ | 30.4686 | 416.65 | 7500 | 29.5594 | 1.0 |
130
+ | 30.3715 | 422.22 | 7600 | 29.3304 | 1.0 |
131
+ | 30.0413 | 427.76 | 7700 | 29.1044 | 1.0 |
132
+ | 29.9067 | 433.32 | 7800 | 28.9034 | 1.0 |
133
+ | 29.5911 | 438.86 | 7900 | 28.7019 | 1.0 |
134
+ | 29.4913 | 444.43 | 8000 | 28.5096 | 1.0 |
135
+ | 29.2069 | 449.97 | 8100 | 28.3284 | 1.0 |
136
+ | 29.1644 | 455.54 | 8200 | 28.1615 | 1.0 |
137
+ | 29.012 | 461.11 | 8300 | 28.0040 | 1.0 |
138
+ | 28.665 | 466.65 | 8400 | 27.8538 | 1.0 |
139
+ | 28.6858 | 472.22 | 8500 | 27.7132 | 1.0 |
140
+ | 28.4118 | 477.76 | 8600 | 27.5848 | 1.0 |
141
+ | 28.3825 | 483.32 | 8700 | 27.4693 | 1.0 |
142
+ | 28.1234 | 488.86 | 8800 | 27.3570 | 1.0 |
143
+ | 28.1963 | 494.43 | 8900 | 27.2488 | 1.0 |
144
+ | 27.9488 | 499.97 | 9000 | 27.1602 | 1.0 |
145
+ | 28.0135 | 505.54 | 9100 | 27.0756 | 1.0 |
146
+ | 27.894 | 511.11 | 9200 | 26.9989 | 1.0 |
147
+ | 27.6633 | 516.65 | 9300 | 26.9334 | 1.0 |
148
+ | 27.768 | 522.22 | 9400 | 26.8775 | 1.0 |
149
+ | 27.6398 | 527.76 | 9500 | 26.8242 | 1.0 |
150
+ | 27.6333 | 533.32 | 9600 | 26.7874 | 1.0 |
151
+ | 27.5064 | 538.86 | 9700 | 26.7575 | 1.0 |
152
+ | 27.601 | 544.43 | 9800 | 26.7354 | 1.0 |
153
+ | 27.4418 | 549.97 | 9900 | 26.7223 | 1.0 |
154
+ | 27.6197 | 555.54 | 10000 | 26.7163 | 1.0 |
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