Hugging Face's logo

anton-l
/
xtreme_s_xlsr_300m_voxpopuli_en

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
English
wav2vec2
voxpopuli
google/xtreme_s
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
anton-l HF staff commited on
Commit
301b9ff
•
1 Parent(s): 45dfb0d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +115 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: xtreme_s_xlsr_300m_voxpopuli_en
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_300m_voxpopuli_en
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: 0.4242
18
+ - Wer: 0.1564
19
+ - Cer: 0.0999
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: 8
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 64
45
+ - total_eval_batch_size: 8
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 2000
49
+ - num_epochs: 10.0
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
56
+ | 1.4221 | 0.19 | 500 | 1.3325 | 0.8224 | 0.3432 |
57
+ | 0.8429 | 0.38 | 1000 | 0.7087 | 0.5028 | 0.2023 |
58
+ | 0.7377 | 0.57 | 1500 | 0.4900 | 0.2778 | 0.1339 |
59
+ | 0.5641 | 0.77 | 2000 | 0.4460 | 0.2540 | 0.1284 |
60
+ | 0.5787 | 0.96 | 2500 | 0.4242 | 0.2148 | 0.1167 |
61
+ | 0.3465 | 1.15 | 3000 | 0.4210 | 0.2087 | 0.1154 |
62
+ | 0.2787 | 1.34 | 3500 | 0.3954 | 0.2090 | 0.1155 |
63
+ | 0.2775 | 1.53 | 4000 | 0.3938 | 0.1992 | 0.1133 |
64
+ | 0.262 | 1.72 | 4500 | 0.3748 | 0.2104 | 0.1151 |
65
+ | 0.3138 | 1.92 | 5000 | 0.3825 | 0.1993 | 0.1134 |
66
+ | 0.4331 | 2.11 | 5500 | 0.3648 | 0.1935 | 0.1104 |
67
+ | 0.3802 | 2.3 | 6000 | 0.3966 | 0.1910 | 0.1109 |
68
+ | 0.3928 | 2.49 | 6500 | 0.3995 | 0.1898 | 0.1100 |
69
+ | 0.3441 | 2.68 | 7000 | 0.3764 | 0.1887 | 0.1103 |
70
+ | 0.3673 | 2.87 | 7500 | 0.3800 | 0.1843 | 0.1086 |
71
+ | 0.3422 | 3.07 | 8000 | 0.3932 | 0.1830 | 0.1092 |
72
+ | 0.2933 | 3.26 | 8500 | 0.3672 | 0.1915 | 0.1104 |
73
+ | 0.1785 | 3.45 | 9000 | 0.3820 | 0.1796 | 0.1072 |
74
+ | 0.321 | 3.64 | 9500 | 0.3533 | 0.1994 | 0.1126 |
75
+ | 0.1673 | 3.83 | 10000 | 0.3683 | 0.1856 | 0.1084 |
76
+ | 0.1757 | 4.02 | 10500 | 0.3365 | 0.1925 | 0.1102 |
77
+ | 0.1881 | 4.22 | 11000 | 0.3528 | 0.1775 | 0.1066 |
78
+ | 0.3106 | 4.41 | 11500 | 0.3909 | 0.1754 | 0.1063 |
79
+ | 0.25 | 4.6 | 12000 | 0.3734 | 0.1723 | 0.1052 |
80
+ | 0.2005 | 4.79 | 12500 | 0.3358 | 0.1900 | 0.1092 |
81
+ | 0.2982 | 4.98 | 13000 | 0.3513 | 0.1766 | 0.1060 |
82
+ | 0.1552 | 5.17 | 13500 | 0.3720 | 0.1729 | 0.1059 |
83
+ | 0.1645 | 5.37 | 14000 | 0.3569 | 0.1713 | 0.1044 |
84
+ | 0.2065 | 5.56 | 14500 | 0.3639 | 0.1720 | 0.1048 |
85
+ | 0.1898 | 5.75 | 15000 | 0.3660 | 0.1726 | 0.1050 |
86
+ | 0.1397 | 5.94 | 15500 | 0.3731 | 0.1670 | 0.1033 |
87
+ | 0.2056 | 6.13 | 16000 | 0.3782 | 0.1650 | 0.1030 |
88
+ | 0.1859 | 6.32 | 16500 | 0.3903 | 0.1667 | 0.1033 |
89
+ | 0.1374 | 6.52 | 17000 | 0.3721 | 0.1736 | 0.1048 |
90
+ | 0.2482 | 6.71 | 17500 | 0.3899 | 0.1643 | 0.1023 |
91
+ | 0.159 | 6.9 | 18000 | 0.3847 | 0.1687 | 0.1032 |
92
+ | 0.1487 | 7.09 | 18500 | 0.3817 | 0.1671 | 0.1030 |
93
+ | 0.1942 | 7.28 | 19000 | 0.4120 | 0.1616 | 0.1018 |
94
+ | 0.1517 | 7.47 | 19500 | 0.3856 | 0.1635 | 0.1020 |
95
+ | 0.0946 | 7.67 | 20000 | 0.3838 | 0.1621 | 0.1016 |
96
+ | 0.1455 | 7.86 | 20500 | 0.3749 | 0.1652 | 0.1020 |
97
+ | 0.1303 | 8.05 | 21000 | 0.4074 | 0.1615 | 0.1011 |
98
+ | 0.1207 | 8.24 | 21500 | 0.4121 | 0.1606 | 0.1008 |
99
+ | 0.0727 | 8.43 | 22000 | 0.3948 | 0.1607 | 0.1009 |
100
+ | 0.1123 | 8.62 | 22500 | 0.4025 | 0.1603 | 0.1009 |
101
+ | 0.1606 | 8.82 | 23000 | 0.3963 | 0.1580 | 0.1004 |
102
+ | 0.1458 | 9.01 | 23500 | 0.3991 | 0.1574 | 0.1002 |
103
+ | 0.2286 | 9.2 | 24000 | 0.4149 | 0.1596 | 0.1009 |
104
+ | 0.1284 | 9.39 | 24500 | 0.4251 | 0.1572 | 0.1002 |
105
+ | 0.1141 | 9.58 | 25000 | 0.4264 | 0.1579 | 0.1002 |
106
+ | 0.1823 | 9.77 | 25500 | 0.4230 | 0.1562 | 0.0999 |
107
+ | 0.2514 | 9.97 | 26000 | 0.4242 | 0.1564 | 0.0999 |
108
+
109
+
110
+ ### Framework versions
111
+
112
+ - Transformers 4.18.0.dev0
113
+ - Pytorch 1.10.1+cu111
114
+ - Datasets 1.18.4.dev0
115
+ - Tokenizers 0.11.6