Hugging Face's logo

anton-l
/
xtreme_s_xlsr_300m_mls

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
google/xtreme_s
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
anton-l HF staff commited on
Commit
55861b1
·
1 Parent(s): 29b5d21

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +116 -0
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: xtreme_s_xlsr_mls
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # xtreme_s_xlsr_mls
14
+
15
+ 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.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.6302
18
+ - Wer: 0.3036
19
+ - Cer: 0.0952
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: 0.0003
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 64
46
+ - total_eval_batch_size: 8
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 3000
50
+ - num_epochs: 100.0
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
57
+ | 3.0446 | 1.91 | 500 | 2.9866 | 1.0 | 1.0 |
58
+ | 0.8789 | 3.82 | 1000 | 0.8574 | 0.7225 | 0.2355 |
59
+ | 0.4766 | 5.72 | 1500 | 0.4813 | 0.4624 | 0.1394 |
60
+ | 0.3779 | 7.63 | 2000 | 0.4465 | 0.4154 | 0.1309 |
61
+ | 0.3244 | 9.54 | 2500 | 0.4213 | 0.3683 | 0.1163 |
62
+ | 0.346 | 11.45 | 3000 | 0.4606 | 0.4033 | 0.1299 |
63
+ | 0.3092 | 13.36 | 3500 | 0.4160 | 0.3585 | 0.1115 |
64
+ | 0.3287 | 15.27 | 4000 | 0.4364 | 0.3631 | 0.1165 |
65
+ | 0.3165 | 17.18 | 4500 | 0.4218 | 0.3451 | 0.1056 |
66
+ | 0.2874 | 19.08 | 5000 | 0.4583 | 0.3650 | 0.1151 |
67
+ | 0.3089 | 20.99 | 5500 | 0.4424 | 0.3485 | 0.1137 |
68
+ | 0.2689 | 22.9 | 6000 | 0.4427 | 0.3542 | 0.1128 |
69
+ | 0.234 | 24.81 | 6500 | 0.4204 | 0.3431 | 0.1069 |
70
+ | 0.2363 | 26.72 | 7000 | 0.4792 | 0.3689 | 0.1191 |
71
+ | 0.2796 | 28.62 | 7500 | 0.4867 | 0.3662 | 0.1154 |
72
+ | 0.2447 | 30.53 | 8000 | 0.4908 | 0.3584 | 0.1160 |
73
+ | 0.22 | 32.44 | 8500 | 0.5315 | 0.3626 | 0.1240 |
74
+ | 0.1961 | 34.35 | 9000 | 0.5121 | 0.3610 | 0.1168 |
75
+ | 0.1959 | 36.26 | 9500 | 0.5140 | 0.3648 | 0.1179 |
76
+ | 0.1748 | 38.17 | 10000 | 0.5464 | 0.3763 | 0.1206 |
77
+ | 0.197 | 40.08 | 10500 | 0.5199 | 0.3515 | 0.1128 |
78
+ | 0.2166 | 41.98 | 11000 | 0.5336 | 0.3607 | 0.1191 |
79
+ | 0.2078 | 43.89 | 11500 | 0.5389 | 0.3518 | 0.1136 |
80
+ | 0.1827 | 45.8 | 12000 | 0.5014 | 0.3287 | 0.1053 |
81
+ | 0.1783 | 47.71 | 12500 | 0.5408 | 0.3545 | 0.1121 |
82
+ | 0.1489 | 49.62 | 13000 | 0.5292 | 0.3472 | 0.1098 |
83
+ | 0.1665 | 51.53 | 13500 | 0.5052 | 0.3300 | 0.1033 |
84
+ | 0.1631 | 53.43 | 14000 | 0.5241 | 0.3362 | 0.1081 |
85
+ | 0.1943 | 55.34 | 14500 | 0.5453 | 0.3373 | 0.1076 |
86
+ | 0.1504 | 57.25 | 15000 | 0.5958 | 0.3594 | 0.1149 |
87
+ | 0.136 | 59.16 | 15500 | 0.5645 | 0.3367 | 0.1082 |
88
+ | 0.1224 | 61.07 | 16000 | 0.5322 | 0.3302 | 0.1039 |
89
+ | 0.1156 | 62.98 | 16500 | 0.5728 | 0.3332 | 0.1061 |
90
+ | 0.114 | 64.88 | 17000 | 0.5994 | 0.3410 | 0.1125 |
91
+ | 0.1445 | 66.79 | 17500 | 0.6048 | 0.3471 | 0.1098 |
92
+ | 0.1281 | 68.7 | 18000 | 0.5747 | 0.3278 | 0.1042 |
93
+ | 0.1233 | 70.61 | 18500 | 0.6021 | 0.3375 | 0.1082 |
94
+ | 0.1109 | 72.52 | 19000 | 0.5851 | 0.3188 | 0.1021 |
95
+ | 0.0943 | 74.43 | 19500 | 0.5944 | 0.3238 | 0.1033 |
96
+ | 0.1418 | 76.34 | 20000 | 0.5904 | 0.3143 | 0.0997 |
97
+ | 0.1317 | 78.24 | 20500 | 0.6291 | 0.3283 | 0.1047 |
98
+ | 0.1177 | 80.15 | 21000 | 0.6114 | 0.3190 | 0.1000 |
99
+ | 0.1138 | 82.06 | 21500 | 0.6155 | 0.3245 | 0.1023 |
100
+ | 0.1074 | 83.97 | 22000 | 0.6094 | 0.3153 | 0.1004 |
101
+ | 0.11 | 85.88 | 22500 | 0.6041 | 0.3141 | 0.0988 |
102
+ | 0.1096 | 87.78 | 23000 | 0.6243 | 0.3110 | 0.0986 |
103
+ | 0.1017 | 89.69 | 23500 | 0.6110 | 0.3121 | 0.0984 |
104
+ | 0.1015 | 91.6 | 24000 | 0.6385 | 0.3093 | 0.0978 |
105
+ | 0.0952 | 93.51 | 24500 | 0.6155 | 0.3036 | 0.0953 |
106
+ | 0.0896 | 95.42 | 25000 | 0.6215 | 0.3033 | 0.0951 |
107
+ | 0.0953 | 97.33 | 25500 | 0.6293 | 0.3037 | 0.0953 |
108
+ | 0.0834 | 99.24 | 26000 | 0.6302 | 0.3036 | 0.0952 |
109
+
110
+
111
+ ### Framework versions
112
+
113
+ - Transformers 4.18.0.dev0
114
+ - Pytorch 1.11.0+cu113
115
+ - Datasets 1.18.4.dev0
116
+ - Tokenizers 0.11.6