Hugging Face's logo

tomascufaro
/
wav2vec2-large-xls-r-300m-spanish-small-v3

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
es
robust-speech-event
Generated from Trainer
Inference Endpoints
Model card Files Community
tomascufaro commited on
Commit
19c45fd
•
1 Parent(s): f0180f6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +155 -0
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - common_voice
6
+ model-index:
7
+ - name: wav2vec2-large-xls-r-300m-spanish-small-v3
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # wav2vec2-large-xls-r-300m-spanish-small-v3
15
+
16
+ This model is a fine-tuned version of [jhonparra18/wav2vec2-large-xls-r-300m-spanish-custom](https://huggingface.co/jhonparra18/wav2vec2-large-xls-r-300m-spanish-custom) on the common_voice dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.3986
19
+ - Wer: 0.1980
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0004
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 500
47
+ - num_epochs: 25
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
+ | 0.2372 | 0.26 | 400 | 0.3011 | 0.2660 |
55
+ | 0.3413 | 0.53 | 800 | 0.3559 | 0.3228 |
56
+ | 0.3598 | 0.79 | 1200 | 0.3753 | 0.3400 |
57
+ | 0.3529 | 1.05 | 1600 | 0.3385 | 0.2979 |
58
+ | 0.3133 | 1.32 | 2000 | 0.3559 | 0.3056 |
59
+ | 0.3158 | 1.58 | 2400 | 0.3364 | 0.2994 |
60
+ | 0.3092 | 1.85 | 2800 | 0.3210 | 0.2876 |
61
+ | 0.2919 | 2.11 | 3200 | 0.3460 | 0.3010 |
62
+ | 0.2666 | 2.37 | 3600 | 0.3543 | 0.3036 |
63
+ | 0.2819 | 2.64 | 4000 | 0.3477 | 0.2959 |
64
+ | 0.283 | 2.9 | 4400 | 0.3492 | 0.2968 |
65
+ | 0.2484 | 3.16 | 4800 | 0.3647 | 0.2993 |
66
+ | 0.2371 | 3.43 | 5200 | 0.3601 | 0.2942 |
67
+ | 0.2382 | 3.69 | 5600 | 0.3656 | 0.3019 |
68
+ | 0.2425 | 3.96 | 6000 | 0.3379 | 0.2873 |
69
+ | 0.2092 | 4.22 | 6400 | 0.3385 | 0.2736 |
70
+ | 0.2171 | 4.48 | 6800 | 0.3503 | 0.2889 |
71
+ | 0.2185 | 4.75 | 7200 | 0.3289 | 0.2727 |
72
+ | 0.2236 | 5.01 | 7600 | 0.3447 | 0.2771 |
73
+ | 0.1882 | 5.27 | 8000 | 0.3586 | 0.2860 |
74
+ | 0.1986 | 5.54 | 8400 | 0.3404 | 0.2829 |
75
+ | 0.2055 | 5.8 | 8800 | 0.3561 | 0.2869 |
76
+ | 0.196 | 6.06 | 9200 | 0.3633 | 0.2811 |
77
+ | 0.1748 | 6.33 | 9600 | 0.3703 | 0.2818 |
78
+ | 0.1758 | 6.59 | 10000 | 0.3525 | 0.2816 |
79
+ | 0.1819 | 6.86 | 10400 | 0.3581 | 0.2765 |
80
+ | 0.1715 | 7.12 | 10800 | 0.3480 | 0.2628 |
81
+ | 0.1606 | 7.38 | 11200 | 0.3490 | 0.2703 |
82
+ | 0.1632 | 7.65 | 11600 | 0.3461 | 0.2706 |
83
+ | 0.1638 | 7.91 | 12000 | 0.3458 | 0.2673 |
84
+ | 0.1552 | 8.17 | 12400 | 0.3646 | 0.2732 |
85
+ | 0.154 | 8.44 | 12800 | 0.3706 | 0.2726 |
86
+ | 0.1512 | 8.7 | 13200 | 0.3609 | 0.2683 |
87
+ | 0.149 | 8.97 | 13600 | 0.3610 | 0.2668 |
88
+ | 0.1357 | 9.23 | 14000 | 0.3693 | 0.2740 |
89
+ | 0.1375 | 9.49 | 14400 | 0.3677 | 0.2625 |
90
+ | 0.1391 | 9.76 | 14800 | 0.3795 | 0.2762 |
91
+ | 0.1378 | 10.02 | 15200 | 0.3541 | 0.2592 |
92
+ | 0.1197 | 10.28 | 15600 | 0.3562 | 0.2507 |
93
+ | 0.1259 | 10.55 | 16000 | 0.3612 | 0.2584 |
94
+ | 0.1266 | 10.81 | 16400 | 0.3470 | 0.2527 |
95
+ | 0.1199 | 11.07 | 16800 | 0.3721 | 0.2571 |
96
+ | 0.1157 | 11.34 | 17200 | 0.3734 | 0.2571 |
97
+ | 0.1107 | 11.6 | 17600 | 0.3730 | 0.2589 |
98
+ | 0.1148 | 11.87 | 18000 | 0.3648 | 0.2536 |
99
+ | 0.1095 | 12.13 | 18400 | 0.3746 | 0.2521 |
100
+ | 0.1047 | 12.39 | 18800 | 0.3566 | 0.2530 |
101
+ | 0.1043 | 12.66 | 19200 | 0.3794 | 0.2545 |
102
+ | 0.1066 | 12.92 | 19600 | 0.3548 | 0.2439 |
103
+ | 0.0974 | 13.18 | 20000 | 0.3702 | 0.2461 |
104
+ | 0.0978 | 13.45 | 20400 | 0.3721 | 0.2492 |
105
+ | 0.095 | 13.71 | 20800 | 0.3599 | 0.2467 |
106
+ | 0.0963 | 13.97 | 21200 | 0.3650 | 0.2402 |
107
+ | 0.0902 | 14.24 | 21600 | 0.3689 | 0.2459 |
108
+ | 0.0898 | 14.5 | 22000 | 0.3832 | 0.2452 |
109
+ | 0.0865 | 14.77 | 22400 | 0.3982 | 0.2436 |
110
+ | 0.0911 | 15.03 | 22800 | 0.3785 | 0.2398 |
111
+ | 0.0793 | 15.29 | 23200 | 0.3731 | 0.2396 |
112
+ | 0.0806 | 15.56 | 23600 | 0.3626 | 0.2372 |
113
+ | 0.0789 | 15.82 | 24000 | 0.3707 | 0.2356 |
114
+ | 0.0779 | 16.08 | 24400 | 0.3850 | 0.2368 |
115
+ | 0.078 | 16.35 | 24800 | 0.3831 | 0.2363 |
116
+ | 0.0732 | 16.61 | 25200 | 0.3947 | 0.2287 |
117
+ | 0.0733 | 16.88 | 25600 | 0.3928 | 0.2374 |
118
+ | 0.0721 | 17.14 | 26000 | 0.3943 | 0.2324 |
119
+ | 0.0676 | 17.4 | 26400 | 0.3793 | 0.2311 |
120
+ | 0.0682 | 17.67 | 26800 | 0.3958 | 0.2257 |
121
+ | 0.0714 | 17.93 | 27200 | 0.3890 | 0.2322 |
122
+ | 0.0673 | 18.19 | 27600 | 0.3872 | 0.2229 |
123
+ | 0.0613 | 18.46 | 28000 | 0.3828 | 0.2226 |
124
+ | 0.0621 | 18.72 | 28400 | 0.3812 | 0.2214 |
125
+ | 0.0622 | 18.98 | 28800 | 0.3919 | 0.2212 |
126
+ | 0.0576 | 19.25 | 29200 | 0.4000 | 0.2205 |
127
+ | 0.0581 | 19.51 | 29600 | 0.3953 | 0.2203 |
128
+ | 0.0573 | 19.78 | 30000 | 0.3947 | 0.2190 |
129
+ | 0.0576 | 20.04 | 30400 | 0.3909 | 0.2156 |
130
+ | 0.0551 | 20.3 | 30800 | 0.4178 | 0.2153 |
131
+ | 0.0525 | 20.57 | 31200 | 0.3935 | 0.2152 |
132
+ | 0.0522 | 20.83 | 31600 | 0.4054 | 0.2151 |
133
+ | 0.0519 | 21.09 | 32000 | 0.3877 | 0.2135 |
134
+ | 0.0479 | 21.36 | 32400 | 0.4119 | 0.2107 |
135
+ | 0.0472 | 21.62 | 32800 | 0.3967 | 0.2091 |
136
+ | 0.048 | 21.89 | 33200 | 0.3812 | 0.2057 |
137
+ | 0.0458 | 22.15 | 33600 | 0.3931 | 0.2043 |
138
+ | 0.0459 | 22.41 | 34000 | 0.3937 | 0.2049 |
139
+ | 0.0448 | 22.68 | 34400 | 0.3900 | 0.2056 |
140
+ | 0.0432 | 22.94 | 34800 | 0.4050 | 0.2049 |
141
+ | 0.0425 | 23.2 | 35200 | 0.3985 | 0.2014 |
142
+ | 0.0415 | 23.47 | 35600 | 0.3976 | 0.2013 |
143
+ | 0.0403 | 23.73 | 36000 | 0.4031 | 0.2018 |
144
+ | 0.04 | 23.99 | 36400 | 0.3996 | 0.2000 |
145
+ | 0.039 | 24.26 | 36800 | 0.3977 | 0.1993 |
146
+ | 0.0406 | 24.52 | 37200 | 0.3967 | 0.2000 |
147
+ | 0.0391 | 24.79 | 37600 | 0.3986 | 0.1980 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.17.0.dev0
153
+ - Pytorch 1.10.2+cu102
154
+ - Datasets 1.18.2.dev0
155
+ - Tokenizers 0.11.0