Hugging Face's logo

saeedmaroof
/
hubert-large-xlsr-common1000asli-demo-colab-dd

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
saeedmaroof commited on
Commit
f028548
•
1 Parent(s): 57d1d0a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +157 -0
README.md ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: hubert-large-xlsr-common1000asli-demo-colab-dd
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
+ # hubert-large-xlsr-common1000asli-demo-colab-dd
16
+
17
+ This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on the common_voice dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.0754
20
+ - Wer: 0.5189
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: 0.0003
40
+ - train_batch_size: 128
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 256
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 1000
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
55
+ | 8.5628 | 10.53 | 400 | 1.4949 | 0.9944 |
56
+ | 0.7496 | 21.05 | 800 | 0.6398 | 0.6917 |
57
+ | 0.3298 | 31.58 | 1200 | 0.6116 | 0.6148 |
58
+ | 0.228 | 42.11 | 1600 | 0.6544 | 0.5835 |
59
+ | 0.17 | 52.63 | 2000 | 0.7028 | 0.5955 |
60
+ | 0.1466 | 63.16 | 2400 | 0.6935 | 0.5992 |
61
+ | 0.1261 | 73.68 | 2800 | 0.7101 | 0.5735 |
62
+ | 0.1109 | 84.21 | 3200 | 0.7360 | 0.5610 |
63
+ | 0.1001 | 94.74 | 3600 | 0.7924 | 0.5604 |
64
+ | 0.0856 | 105.26 | 4000 | 0.7975 | 0.5653 |
65
+ | 0.0821 | 115.79 | 4400 | 0.8027 | 0.5611 |
66
+ | 0.0783 | 126.32 | 4800 | 0.8238 | 0.5566 |
67
+ | 0.0691 | 136.84 | 5200 | 0.8109 | 0.5519 |
68
+ | 0.0627 | 147.37 | 5600 | 0.8231 | 0.5544 |
69
+ | 0.0589 | 157.89 | 6000 | 0.8747 | 0.5506 |
70
+ | 0.0548 | 168.42 | 6400 | 0.8440 | 0.5478 |
71
+ | 0.052 | 178.95 | 6800 | 0.8289 | 0.5393 |
72
+ | 0.0471 | 189.47 | 7200 | 0.8689 | 0.5492 |
73
+ | 0.0486 | 200.0 | 7600 | 0.8437 | 0.5372 |
74
+ | 0.0433 | 210.53 | 8000 | 0.8360 | 0.5453 |
75
+ | 0.0419 | 221.05 | 8400 | 0.8645 | 0.5391 |
76
+ | 0.0393 | 231.58 | 8800 | 0.8821 | 0.5506 |
77
+ | 0.0404 | 242.11 | 9200 | 0.9073 | 0.5419 |
78
+ | 1.318 | 252.63 | 9600 | 0.8408 | 0.5813 |
79
+ | 0.0489 | 263.16 | 10000 | 0.8206 | 0.5449 |
80
+ | 0.0406 | 273.68 | 10400 | 0.8592 | 0.5466 |
81
+ | 0.0359 | 284.21 | 10800 | 0.8597 | 0.5476 |
82
+ | 0.0344 | 294.74 | 11200 | 0.8349 | 0.5369 |
83
+ | 0.032 | 305.26 | 11600 | 0.8352 | 0.5379 |
84
+ | 0.0299 | 315.79 | 12000 | 0.8409 | 0.5420 |
85
+ | 0.0287 | 326.32 | 12400 | 0.8562 | 0.5441 |
86
+ | 0.0292 | 336.84 | 12800 | 0.9100 | 0.5519 |
87
+ | 0.0258 | 347.37 | 13200 | 0.9213 | 0.5447 |
88
+ | 0.0229 | 357.89 | 13600 | 0.9020 | 0.5343 |
89
+ | 0.0257 | 368.42 | 14000 | 0.9219 | 0.5531 |
90
+ | 0.0236 | 378.95 | 14400 | 0.9301 | 0.5516 |
91
+ | 0.0241 | 389.47 | 14800 | 0.9058 | 0.5359 |
92
+ | 0.022 | 400.0 | 15200 | 0.9067 | 0.5408 |
93
+ | 3.4199 | 410.53 | 15600 | 0.9661 | 0.6957 |
94
+ | 0.0554 | 421.05 | 16000 | 0.8984 | 0.5661 |
95
+ | 0.0289 | 431.58 | 16400 | 0.8843 | 0.5504 |
96
+ | 0.0234 | 442.11 | 16800 | 0.8943 | 0.5407 |
97
+ | 0.0219 | 452.63 | 17200 | 0.9325 | 0.5391 |
98
+ | 0.0194 | 463.16 | 17600 | 0.9588 | 0.5442 |
99
+ | 0.0195 | 473.68 | 18000 | 0.9660 | 0.5478 |
100
+ | 0.0184 | 484.21 | 18400 | 0.9325 | 0.5394 |
101
+ | 0.0178 | 494.74 | 18800 | 0.9526 | 0.5435 |
102
+ | 0.0171 | 505.26 | 19200 | 0.9533 | 0.5412 |
103
+ | 0.0174 | 515.79 | 19600 | 0.8962 | 0.5410 |
104
+ | 0.0165 | 526.32 | 20000 | 0.9699 | 0.5422 |
105
+ | 0.0153 | 536.84 | 20400 | 0.9252 | 0.5301 |
106
+ | 0.0141 | 547.37 | 20800 | 0.9364 | 0.5401 |
107
+ | 0.0148 | 557.89 | 21200 | 0.9479 | 0.5387 |
108
+ | 0.0141 | 568.42 | 21600 | 0.9692 | 0.5365 |
109
+ | 0.0136 | 578.95 | 22000 | 0.9779 | 0.5343 |
110
+ | 0.0127 | 589.47 | 22400 | 0.9684 | 0.5303 |
111
+ | 0.0122 | 600.0 | 22800 | 0.9930 | 0.5346 |
112
+ | 0.0122 | 610.53 | 23200 | 0.9733 | 0.5348 |
113
+ | 0.0112 | 621.05 | 23600 | 1.0059 | 0.5374 |
114
+ | 0.0113 | 631.58 | 24000 | 0.9801 | 0.5302 |
115
+ | 0.0114 | 642.11 | 24400 | 0.9901 | 0.5336 |
116
+ | 0.0101 | 652.63 | 24800 | 0.9943 | 0.5383 |
117
+ | 0.0106 | 663.16 | 25200 | 1.0296 | 0.5272 |
118
+ | 0.0099 | 673.68 | 25600 | 1.0321 | 0.5294 |
119
+ | 0.01 | 684.21 | 26000 | 1.0282 | 0.5310 |
120
+ | 0.01 | 694.74 | 26400 | 1.0336 | 0.5326 |
121
+ | 0.009 | 705.26 | 26800 | 1.0130 | 0.5247 |
122
+ | 0.0087 | 715.79 | 27200 | 1.0326 | 0.5261 |
123
+ | 0.0086 | 726.32 | 27600 | 1.0343 | 0.5255 |
124
+ | 0.0085 | 736.84 | 28000 | 1.0009 | 0.5338 |
125
+ | 0.0086 | 747.37 | 28400 | 1.0369 | 0.5279 |
126
+ | 0.008 | 757.89 | 28800 | 1.0063 | 0.5326 |
127
+ | 0.0095 | 768.42 | 29200 | 1.0152 | 0.5238 |
128
+ | 0.0072 | 778.95 | 29600 | 1.0313 | 0.5263 |
129
+ | 0.0073 | 789.47 | 30000 | 1.0440 | 0.5229 |
130
+ | 0.0068 | 800.0 | 30400 | 1.0348 | 0.5257 |
131
+ | 0.0076 | 810.53 | 30800 | 1.0040 | 0.5237 |
132
+ | 0.007 | 821.05 | 31200 | 1.0382 | 0.5205 |
133
+ | 0.0069 | 831.58 | 31600 | 1.0217 | 0.5276 |
134
+ | 0.0064 | 842.11 | 32000 | 1.0425 | 0.5301 |
135
+ | 0.0067 | 852.63 | 32400 | 1.0384 | 0.5262 |
136
+ | 0.006 | 863.16 | 32800 | 1.0698 | 0.5294 |
137
+ | 0.0058 | 873.68 | 33200 | 1.0412 | 0.5229 |
138
+ | 0.0063 | 884.21 | 33600 | 1.0423 | 0.5225 |
139
+ | 0.0053 | 894.74 | 34000 | 1.0554 | 0.5213 |
140
+ | 0.0055 | 905.26 | 34400 | 1.0593 | 0.5202 |
141
+ | 0.0051 | 915.79 | 34800 | 1.0716 | 0.5211 |
142
+ | 0.0052 | 926.32 | 35200 | 1.0668 | 0.5182 |
143
+ | 0.0048 | 936.84 | 35600 | 1.0840 | 0.5209 |
144
+ | 0.0052 | 947.37 | 36000 | 1.0633 | 0.5173 |
145
+ | 0.0046 | 957.89 | 36400 | 1.0747 | 0.5184 |
146
+ | 0.0051 | 968.42 | 36800 | 1.0766 | 0.5190 |
147
+ | 0.0052 | 978.95 | 37200 | 1.0748 | 0.5194 |
148
+ | 0.005 | 989.47 | 37600 | 1.0778 | 0.5186 |
149
+ | 0.005 | 1000.0 | 38000 | 1.0754 | 0.5189 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - Transformers 4.11.3
155
+ - Pytorch 1.10.0+cu102
156
+ - Datasets 1.13.3
157
+ - Tokenizers 0.10.3