Hugging Face's logo

lgris
/
wav2vec2-xls-r-gn-cv7

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Guaraní
wav2vec2
generated_from_trainer
robust-speech-event
hf-asr-leaderboard
Eval Results
Inference Endpoints
Model card Files Metrics Community
lgris commited on
Commit
5b39261
•
1 Parent(s): 04e8447

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +192 -0
README.md ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: wav2vec2-xls-r-gn-cv7
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
+ # wav2vec2-xls-r-gn-cv7
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 common_voice dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.7197
20
+ - Wer: 0.7434
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: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 16
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 100
48
+ - training_steps: 13000
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
55
+ | 3.4669 | 6.24 | 100 | 3.3003 | 1.0 |
56
+ | 3.3214 | 12.48 | 200 | 3.2090 | 1.0 |
57
+ | 3.1619 | 18.73 | 300 | 2.6322 | 1.0 |
58
+ | 1.751 | 24.97 | 400 | 1.4089 | 0.9803 |
59
+ | 0.7997 | 31.24 | 500 | 0.9996 | 0.9211 |
60
+ | 0.4996 | 37.48 | 600 | 0.9879 | 0.8553 |
61
+ | 0.3677 | 43.73 | 700 | 0.9543 | 0.8289 |
62
+ | 0.2851 | 49.97 | 800 | 1.0627 | 0.8487 |
63
+ | 0.2556 | 56.24 | 900 | 1.0933 | 0.8355 |
64
+ | 0.2268 | 62.48 | 1000 | 0.9191 | 0.8026 |
65
+ | 0.1914 | 68.73 | 1100 | 0.9582 | 0.7961 |
66
+ | 0.1749 | 74.97 | 1200 | 1.0502 | 0.8092 |
67
+ | 0.157 | 81.24 | 1300 | 0.9998 | 0.7632 |
68
+ | 0.1505 | 87.48 | 1400 | 1.0076 | 0.7303 |
69
+ | 0.1278 | 93.73 | 1500 | 0.9321 | 0.75 |
70
+ | 0.1078 | 99.97 | 1600 | 1.0383 | 0.7697 |
71
+ | 0.1156 | 106.24 | 1700 | 1.0302 | 0.7763 |
72
+ | 0.1107 | 112.48 | 1800 | 1.0419 | 0.7763 |
73
+ | 0.091 | 118.73 | 1900 | 1.0694 | 0.75 |
74
+ | 0.0829 | 124.97 | 2000 | 1.0257 | 0.7829 |
75
+ | 0.0865 | 131.24 | 2100 | 1.2108 | 0.7368 |
76
+ | 0.0907 | 137.48 | 2200 | 1.0458 | 0.7697 |
77
+ | 0.0897 | 143.73 | 2300 | 1.1504 | 0.7895 |
78
+ | 0.0766 | 149.97 | 2400 | 1.1663 | 0.7237 |
79
+ | 0.0659 | 156.24 | 2500 | 1.1320 | 0.7632 |
80
+ | 0.0699 | 162.48 | 2600 | 1.2586 | 0.7434 |
81
+ | 0.0613 | 168.73 | 2700 | 1.1815 | 0.8158 |
82
+ | 0.0598 | 174.97 | 2800 | 1.3299 | 0.75 |
83
+ | 0.0577 | 181.24 | 2900 | 1.2035 | 0.7171 |
84
+ | 0.0576 | 187.48 | 3000 | 1.2134 | 0.7434 |
85
+ | 0.0518 | 193.73 | 3100 | 1.3406 | 0.7566 |
86
+ | 0.0524 | 199.97 | 3200 | 1.4251 | 0.75 |
87
+ | 0.0467 | 206.24 | 3300 | 1.3533 | 0.7697 |
88
+ | 0.0428 | 212.48 | 3400 | 1.2463 | 0.7368 |
89
+ | 0.0453 | 218.73 | 3500 | 1.4532 | 0.7566 |
90
+ | 0.0473 | 224.97 | 3600 | 1.3152 | 0.7434 |
91
+ | 0.0451 | 231.24 | 3700 | 1.2232 | 0.7368 |
92
+ | 0.0361 | 237.48 | 3800 | 1.2938 | 0.7171 |
93
+ | 0.045 | 243.73 | 3900 | 1.4148 | 0.7434 |
94
+ | 0.0422 | 249.97 | 4000 | 1.3786 | 0.7961 |
95
+ | 0.036 | 256.24 | 4100 | 1.4488 | 0.7697 |
96
+ | 0.0352 | 262.48 | 4200 | 1.2294 | 0.6776 |
97
+ | 0.0326 | 268.73 | 4300 | 1.2796 | 0.6974 |
98
+ | 0.034 | 274.97 | 4400 | 1.3805 | 0.7303 |
99
+ | 0.0305 | 281.24 | 4500 | 1.4994 | 0.7237 |
100
+ | 0.0325 | 287.48 | 4600 | 1.4330 | 0.6908 |
101
+ | 0.0338 | 293.73 | 4700 | 1.3091 | 0.7368 |
102
+ | 0.0306 | 299.97 | 4800 | 1.2174 | 0.7171 |
103
+ | 0.0299 | 306.24 | 4900 | 1.3527 | 0.7763 |
104
+ | 0.0287 | 312.48 | 5000 | 1.3651 | 0.7368 |
105
+ | 0.0274 | 318.73 | 5100 | 1.4337 | 0.7368 |
106
+ | 0.0258 | 324.97 | 5200 | 1.3831 | 0.6908 |
107
+ | 0.022 | 331.24 | 5300 | 1.3556 | 0.6974 |
108
+ | 0.021 | 337.48 | 5400 | 1.3836 | 0.7237 |
109
+ | 0.0241 | 343.73 | 5500 | 1.4352 | 0.7039 |
110
+ | 0.0229 | 349.97 | 5600 | 1.3904 | 0.7105 |
111
+ | 0.026 | 356.24 | 5700 | 1.4131 | 0.7171 |
112
+ | 0.021 | 362.48 | 5800 | 1.5426 | 0.6974 |
113
+ | 0.0191 | 368.73 | 5900 | 1.5960 | 0.7632 |
114
+ | 0.0227 | 374.97 | 6000 | 1.6240 | 0.7368 |
115
+ | 0.0204 | 381.24 | 6100 | 1.4301 | 0.7105 |
116
+ | 0.0175 | 387.48 | 6200 | 1.5554 | 0.75 |
117
+ | 0.0183 | 393.73 | 6300 | 1.6044 | 0.7697 |
118
+ | 0.0183 | 399.97 | 6400 | 1.5963 | 0.7368 |
119
+ | 0.016 | 406.24 | 6500 | 1.5679 | 0.7829 |
120
+ | 0.0178 | 412.48 | 6600 | 1.5928 | 0.7697 |
121
+ | 0.014 | 418.73 | 6700 | 1.7000 | 0.7632 |
122
+ | 0.0182 | 424.97 | 6800 | 1.5340 | 0.75 |
123
+ | 0.0148 | 431.24 | 6900 | 1.9274 | 0.7368 |
124
+ | 0.0148 | 437.48 | 7000 | 1.6437 | 0.7697 |
125
+ | 0.0173 | 443.73 | 7100 | 1.5468 | 0.75 |
126
+ | 0.0109 | 449.97 | 7200 | 1.6083 | 0.75 |
127
+ | 0.0167 | 456.24 | 7300 | 1.6732 | 0.75 |
128
+ | 0.0139 | 462.48 | 7400 | 1.5097 | 0.7237 |
129
+ | 0.013 | 468.73 | 7500 | 1.5947 | 0.7171 |
130
+ | 0.0128 | 474.97 | 7600 | 1.6260 | 0.7105 |
131
+ | 0.0166 | 481.24 | 7700 | 1.5756 | 0.7237 |
132
+ | 0.0127 | 487.48 | 7800 | 1.4506 | 0.6908 |
133
+ | 0.013 | 493.73 | 7900 | 1.4882 | 0.7368 |
134
+ | 0.0125 | 499.97 | 8000 | 1.5589 | 0.7829 |
135
+ | 0.0141 | 506.24 | 8100 | 1.6328 | 0.7434 |
136
+ | 0.0115 | 512.48 | 8200 | 1.6586 | 0.7434 |
137
+ | 0.0117 | 518.73 | 8300 | 1.6043 | 0.7105 |
138
+ | 0.009 | 524.97 | 8400 | 1.6508 | 0.7237 |
139
+ | 0.0108 | 531.24 | 8500 | 1.4507 | 0.6974 |
140
+ | 0.011 | 537.48 | 8600 | 1.5942 | 0.7434 |
141
+ | 0.009 | 543.73 | 8700 | 1.8121 | 0.7697 |
142
+ | 0.0112 | 549.97 | 8800 | 1.6923 | 0.7697 |
143
+ | 0.0073 | 556.24 | 8900 | 1.7096 | 0.7368 |
144
+ | 0.0098 | 562.48 | 9000 | 1.7052 | 0.7829 |
145
+ | 0.0088 | 568.73 | 9100 | 1.6956 | 0.7566 |
146
+ | 0.0099 | 574.97 | 9200 | 1.4909 | 0.7171 |
147
+ | 0.0075 | 581.24 | 9300 | 1.6307 | 0.7697 |
148
+ | 0.0077 | 587.48 | 9400 | 1.6196 | 0.7961 |
149
+ | 0.0088 | 593.73 | 9500 | 1.6119 | 0.7566 |
150
+ | 0.0085 | 599.97 | 9600 | 1.4512 | 0.7368 |
151
+ | 0.0086 | 606.24 | 9700 | 1.5992 | 0.7237 |
152
+ | 0.0109 | 612.48 | 9800 | 1.4706 | 0.7368 |
153
+ | 0.0098 | 618.73 | 9900 | 1.3824 | 0.7171 |
154
+ | 0.0091 | 624.97 | 10000 | 1.4776 | 0.6974 |
155
+ | 0.0072 | 631.24 | 10100 | 1.4896 | 0.7039 |
156
+ | 0.0087 | 637.48 | 10200 | 1.5467 | 0.7368 |
157
+ | 0.007 | 643.73 | 10300 | 1.5493 | 0.75 |
158
+ | 0.0076 | 649.97 | 10400 | 1.5706 | 0.7303 |
159
+ | 0.0085 | 656.24 | 10500 | 1.5748 | 0.7237 |
160
+ | 0.0075 | 662.48 | 10600 | 1.5081 | 0.7105 |
161
+ | 0.0068 | 668.73 | 10700 | 1.4967 | 0.6842 |
162
+ | 0.0117 | 674.97 | 10800 | 1.4986 | 0.7105 |
163
+ | 0.0054 | 681.24 | 10900 | 1.5587 | 0.7303 |
164
+ | 0.0059 | 687.48 | 11000 | 1.5886 | 0.7171 |
165
+ | 0.0071 | 693.73 | 11100 | 1.5746 | 0.7171 |
166
+ | 0.0048 | 699.97 | 11200 | 1.6166 | 0.7237 |
167
+ | 0.0048 | 706.24 | 11300 | 1.6098 | 0.7237 |
168
+ | 0.0056 | 712.48 | 11400 | 1.5834 | 0.7237 |
169
+ | 0.0048 | 718.73 | 11500 | 1.5653 | 0.7171 |
170
+ | 0.0045 | 724.97 | 11600 | 1.6252 | 0.7237 |
171
+ | 0.0068 | 731.24 | 11700 | 1.6794 | 0.7171 |
172
+ | 0.0044 | 737.48 | 11800 | 1.6881 | 0.7039 |
173
+ | 0.008 | 743.73 | 11900 | 1.7393 | 0.75 |
174
+ | 0.0045 | 749.97 | 12000 | 1.6869 | 0.7237 |
175
+ | 0.0047 | 756.24 | 12100 | 1.7105 | 0.7303 |
176
+ | 0.0057 | 762.48 | 12200 | 1.7439 | 0.7303 |
177
+ | 0.004 | 768.73 | 12300 | 1.7871 | 0.7434 |
178
+ | 0.0061 | 774.97 | 12400 | 1.7812 | 0.7303 |
179
+ | 0.005 | 781.24 | 12500 | 1.7410 | 0.7434 |
180
+ | 0.0056 | 787.48 | 12600 | 1.7220 | 0.7303 |
181
+ | 0.0064 | 793.73 | 12700 | 1.7141 | 0.7434 |
182
+ | 0.0042 | 799.97 | 12800 | 1.7139 | 0.7368 |
183
+ | 0.0049 | 806.24 | 12900 | 1.7211 | 0.7434 |
184
+ | 0.0044 | 812.48 | 13000 | 1.7197 | 0.7434 |
185
+
186
+
187
+ ### Framework versions
188
+
189
+ - Transformers 4.15.0
190
+ - Pytorch 1.10.0+cu111
191
+ - Datasets 1.18.0
192
+ - Tokenizers 0.10.3