Hugging Face's logo

slplab
/
apac_5sents_XLS-R_2_e-4_unfreeze

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
1
slplab commited on
Commit
11c928c
·
1 Parent(s): 43f3646

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_unfreeze
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_unfreeze
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: 0.9903
20
+ - Wer: 0.2031
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
+ | 189.2127 | 11.11 | 200 | 73.2720 | 1.0 |
56
+ | 54.2997 | 22.22 | 400 | 34.4132 | 1.0 |
57
+ | 20.0866 | 33.32 | 600 | 8.5765 | 1.0 |
58
+ | 6.0035 | 44.43 | 800 | 4.9753 | 1.0 |
59
+ | 4.7213 | 55.54 | 1000 | 4.3482 | 1.0 |
60
+ | 3.4429 | 66.65 | 1200 | 3.1173 | 1.0 |
61
+ | 1.5676 | 77.76 | 1400 | 1.7944 | 0.9353 |
62
+ | 0.7909 | 88.86 | 1600 | 1.6430 | 0.9308 |
63
+ | 0.6096 | 99.97 | 1800 | 1.5703 | 0.9330 |
64
+ | 0.5121 | 111.11 | 2000 | 1.5256 | 0.9129 |
65
+ | 0.4618 | 122.22 | 2200 | 1.6791 | 0.8638 |
66
+ | 0.3701 | 133.32 | 2400 | 1.5437 | 0.6920 |
67
+ | 0.2753 | 144.43 | 2600 | 1.3421 | 0.8304 |
68
+ | 0.1842 | 155.54 | 2800 | 1.1704 | 0.7455 |
69
+ | 0.0994 | 166.65 | 3000 | 1.0909 | 0.4710 |
70
+ | 0.0719 | 177.76 | 3200 | 1.2866 | 0.5335 |
71
+ | 0.0457 | 188.86 | 3400 | 1.1482 | 0.5580 |
72
+ | 0.0373 | 199.97 | 3600 | 0.9844 | 0.6183 |
73
+ | 0.0384 | 211.11 | 3800 | 1.1314 | 0.6451 |
74
+ | 0.0329 | 222.22 | 4000 | 1.3817 | 0.6406 |
75
+ | 0.03 | 233.32 | 4200 | 1.0517 | 0.6049 |
76
+ | 0.026 | 244.43 | 4400 | 1.0459 | 0.5022 |
77
+ | 0.0339 | 255.54 | 4600 | 1.2741 | 0.4732 |
78
+ | 0.0231 | 266.65 | 4800 | 1.5190 | 0.5424 |
79
+ | 0.0244 | 277.76 | 5000 | 1.3602 | 0.6451 |
80
+ | 0.017 | 288.86 | 5200 | 1.9874 | 0.6473 |
81
+ | 0.0204 | 299.97 | 5400 | 1.4477 | 0.6540 |
82
+ | 0.0221 | 311.11 | 5600 | 1.1082 | 0.5960 |
83
+ | 0.019 | 322.22 | 5800 | 1.5668 | 0.5737 |
84
+ | 0.0148 | 333.32 | 6000 | 0.9671 | 0.5871 |
85
+ | 0.0171 | 344.43 | 6200 | 1.0411 | 0.6406 |
86
+ | 0.0135 | 355.54 | 6400 | 1.0979 | 0.5938 |
87
+ | 0.0236 | 366.65 | 6600 | 1.2793 | 0.5670 |
88
+ | 0.0178 | 377.76 | 6800 | 1.6185 | 0.5982 |
89
+ | 0.0145 | 388.86 | 7000 | 1.1957 | 0.5491 |
90
+ | 0.015 | 399.97 | 7200 | 1.6764 | 0.6272 |
91
+ | 0.0122 | 411.11 | 7400 | 1.0150 | 0.6183 |
92
+ | 0.0112 | 422.22 | 7600 | 1.0519 | 0.6429 |
93
+ | 0.0083 | 433.32 | 7800 | 1.2191 | 0.5714 |
94
+ | 0.0086 | 444.43 | 8000 | 1.3643 | 0.6116 |
95
+ | 0.0149 | 455.54 | 8200 | 0.8175 | 0.6116 |
96
+ | 0.0113 | 466.65 | 8400 | 1.3835 | 0.6161 |
97
+ | 0.0085 | 477.76 | 8600 | 1.1749 | 0.5781 |
98
+ | 0.0074 | 488.86 | 8800 | 1.4239 | 0.4754 |
99
+ | 0.0064 | 499.97 | 9000 | 1.2462 | 0.5871 |
100
+ | 0.0089 | 511.11 | 9200 | 0.9149 | 0.4754 |
101
+ | 0.0084 | 522.22 | 9400 | 0.9334 | 0.5759 |
102
+ | 0.0056 | 533.32 | 9600 | 1.2457 | 0.6585 |
103
+ | 0.007 | 544.43 | 9800 | 1.1244 | 0.6518 |
104
+ | 0.0106 | 555.54 | 10000 | 1.2021 | 0.6272 |
105
+ | 0.0082 | 566.65 | 10200 | 1.0176 | 0.6094 |
106
+ | 0.0094 | 577.76 | 10400 | 1.0082 | 0.6161 |
107
+ | 0.0085 | 588.86 | 10600 | 1.0985 | 0.5580 |
108
+ | 0.0087 | 599.97 | 10800 | 0.8951 | 0.5067 |
109
+ | 0.0088 | 611.11 | 11000 | 1.0105 | 0.6094 |
110
+ | 0.0073 | 622.22 | 11200 | 1.1884 | 0.6071 |
111
+ | 0.0058 | 633.32 | 11400 | 1.0784 | 0.5804 |
112
+ | 0.008 | 644.43 | 11600 | 0.9484 | 0.6228 |
113
+ | 0.0044 | 655.54 | 11800 | 0.9366 | 0.6295 |
114
+ | 0.0049 | 666.65 | 12000 | 0.9724 | 0.6562 |
115
+ | 0.0055 | 677.76 | 12200 | 1.0735 | 0.6272 |
116
+ | 0.0057 | 688.86 | 12400 | 1.4276 | 0.5670 |
117
+ | 0.0069 | 699.97 | 12600 | 0.8726 | 0.6004 |
118
+ | 0.0042 | 711.11 | 12800 | 1.2411 | 0.5402 |
119
+ | 0.0031 | 722.22 | 13000 | 0.9987 | 0.5603 |
120
+ | 0.0033 | 733.32 | 13200 | 1.0106 | 0.5781 |
121
+ | 0.0046 | 744.43 | 13400 | 1.0548 | 0.4241 |
122
+ | 0.0042 | 755.54 | 13600 | 0.9983 | 0.2009 |
123
+ | 0.0025 | 766.65 | 13800 | 1.0933 | 0.2879 |
124
+ | 0.0067 | 777.76 | 14000 | 1.0665 | 0.3482 |
125
+ | 0.0061 | 788.86 | 14200 | 1.3937 | 0.4085 |
126
+ | 0.0058 | 799.97 | 14400 | 1.4818 | 0.3036 |
127
+ | 0.003 | 811.11 | 14600 | 1.3054 | 0.2723 |
128
+ | 0.0036 | 822.22 | 14800 | 1.1874 | 0.4062 |
129
+ | 0.0032 | 833.32 | 15000 | 1.4134 | 0.3571 |
130
+ | 0.0024 | 844.43 | 15200 | 1.4457 | 0.3661 |
131
+ | 0.0019 | 855.54 | 15400 | 1.2084 | 0.4821 |
132
+ | 0.0014 | 866.65 | 15600 | 1.2791 | 0.3058 |
133
+ | 0.0018 | 877.76 | 15800 | 1.1289 | 0.3616 |
134
+ | 0.0013 | 888.86 | 16000 | 1.3066 | 0.2567 |
135
+ | 0.001 | 899.97 | 16200 | 1.3964 | 0.2991 |
136
+ | 0.0016 | 911.11 | 16400 | 1.3610 | 0.2522 |
137
+ | 0.001 | 922.22 | 16600 | 1.4205 | 0.2812 |
138
+ | 0.0015 | 933.32 | 16800 | 1.2090 | 0.2946 |
139
+ | 0.0009 | 944.43 | 17000 | 1.2032 | 0.2344 |
140
+ | 0.0018 | 955.54 | 17200 | 1.2981 | 0.3013 |
141
+ | 0.0014 | 966.65 | 17400 | 1.2368 | 0.3549 |
142
+ | 0.0016 | 977.76 | 17600 | 1.3524 | 0.3683 |
143
+ | 0.0009 | 988.86 | 17800 | 1.4152 | 0.3460 |
144
+ | 0.0007 | 999.97 | 18000 | 1.3977 | 0.3125 |
145
+ | 0.0015 | 1011.11 | 18200 | 1.3225 | 0.2857 |
146
+ | 0.0009 | 1022.22 | 18400 | 1.2686 | 0.2812 |
147
+ | 0.0009 | 1033.32 | 18600 | 1.2383 | 0.3036 |
148
+ | 0.0011 | 1044.43 | 18800 | 1.2066 | 0.2902 |
149
+ | 0.0009 | 1055.54 | 19000 | 1.2048 | 0.2812 |
150
+ | 0.0007 | 1066.65 | 19200 | 1.2001 | 0.2812 |
151
+ | 0.0009 | 1077.76 | 19400 | 1.2631 | 0.3013 |
152
+ | 0.0005 | 1088.86 | 19600 | 1.2438 | 0.3036 |
153
+ | 0.0005 | 1099.97 | 19800 | 1.2146 | 0.3036 |
154
+ | 0.0005 | 1111.11 | 20000 | 1.2095 | 0.2991 |
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