Hugging Face's logo

anton-l
/
xtreme_s_xlsr_300m_fleurs_asr_western_european

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Allar
wav2vec2
fleurs-asr
google/xtreme_s
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
anton-l HF staff commited on
Commit
e2c1514
·
1 Parent(s): 22df849

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +104 -0
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: xtreme_s_xlsr_300m_fleurs_asr_western_european_nomask
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_fleurs_asr_western_european_nomask
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: 1.2572
18
+ - Wer: 0.6278
19
+ - Cer: 0.2394
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: 1000
49
+ - num_epochs: 20.0
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
56
+ | 3.1411 | 0.49 | 500 | 3.1673 | 1.0 | 1.0 |
57
+ | 0.6397 | 0.97 | 1000 | 0.9039 | 0.7171 | 0.2862 |
58
+ | 0.4033 | 1.46 | 1500 | 0.8914 | 0.6862 | 0.2763 |
59
+ | 0.3473 | 1.94 | 2000 | 0.8017 | 0.6505 | 0.2536 |
60
+ | 0.3143 | 2.43 | 2500 | 0.8568 | 0.6566 | 0.2627 |
61
+ | 0.3004 | 2.91 | 3000 | 0.8898 | 0.6640 | 0.2686 |
62
+ | 0.282 | 3.4 | 3500 | 0.8489 | 0.6637 | 0.2571 |
63
+ | 0.2489 | 3.88 | 4000 | 0.8955 | 0.6744 | 0.2691 |
64
+ | 0.1706 | 4.37 | 4500 | 0.9190 | 0.6788 | 0.2688 |
65
+ | 0.3336 | 4.85 | 5000 | 0.8915 | 0.6594 | 0.2572 |
66
+ | 0.1426 | 5.34 | 5500 | 0.9501 | 0.6784 | 0.2686 |
67
+ | 0.2301 | 5.83 | 6000 | 1.0217 | 0.6719 | 0.2735 |
68
+ | 0.1325 | 6.31 | 6500 | 0.9578 | 0.6691 | 0.2655 |
69
+ | 0.1145 | 6.8 | 7000 | 0.9129 | 0.6680 | 0.2593 |
70
+ | 0.1202 | 7.28 | 7500 | 0.9646 | 0.6749 | 0.2619 |
71
+ | 0.143 | 7.77 | 8000 | 0.9200 | 0.6554 | 0.2554 |
72
+ | 0.1012 | 8.25 | 8500 | 0.9553 | 0.6787 | 0.2628 |
73
+ | 0.1018 | 8.74 | 9000 | 0.9455 | 0.6445 | 0.2511 |
74
+ | 0.1148 | 9.22 | 9500 | 1.0206 | 0.6725 | 0.2629 |
75
+ | 0.0794 | 9.71 | 10000 | 0.9305 | 0.6547 | 0.2526 |
76
+ | 0.2891 | 10.19 | 10500 | 1.0424 | 0.6709 | 0.2570 |
77
+ | 0.1665 | 10.68 | 11000 | 0.9760 | 0.6596 | 0.2507 |
78
+ | 0.1956 | 11.17 | 11500 | 0.9549 | 0.6340 | 0.2440 |
79
+ | 0.0828 | 11.65 | 12000 | 0.9598 | 0.6403 | 0.2460 |
80
+ | 0.059 | 12.14 | 12500 | 0.9972 | 0.6574 | 0.2531 |
81
+ | 0.0505 | 12.62 | 13000 | 0.9836 | 0.6534 | 0.2525 |
82
+ | 0.0336 | 13.11 | 13500 | 1.0619 | 0.6564 | 0.2519 |
83
+ | 0.0435 | 13.59 | 14000 | 1.0844 | 0.6480 | 0.2543 |
84
+ | 0.0216 | 14.08 | 14500 | 1.1084 | 0.6512 | 0.2521 |
85
+ | 0.0265 | 14.56 | 15000 | 1.1152 | 0.6607 | 0.2563 |
86
+ | 0.0975 | 15.05 | 15500 | 1.1060 | 0.6456 | 0.2471 |
87
+ | 0.1396 | 15.53 | 16000 | 1.1100 | 0.6337 | 0.2418 |
88
+ | 0.0701 | 16.02 | 16500 | 1.1731 | 0.6309 | 0.2415 |
89
+ | 0.1171 | 16.5 | 17000 | 1.1302 | 0.6315 | 0.2396 |
90
+ | 0.0778 | 16.99 | 17500 | 1.1485 | 0.6379 | 0.2447 |
91
+ | 0.0642 | 17.48 | 18000 | 1.2009 | 0.6400 | 0.2464 |
92
+ | 0.0322 | 17.96 | 18500 | 1.2028 | 0.6357 | 0.2425 |
93
+ | 0.031 | 18.45 | 19000 | 1.2381 | 0.6285 | 0.2416 |
94
+ | 0.0579 | 18.93 | 19500 | 1.2299 | 0.6265 | 0.2409 |
95
+ | 0.0628 | 19.42 | 20000 | 1.2582 | 0.6277 | 0.2395 |
96
+ | 0.074 | 19.9 | 20500 | 1.2572 | 0.6278 | 0.2394 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.18.0.dev0
102
+ - Pytorch 1.10.1+cu111
103
+ - Datasets 1.18.4.dev0
104
+ - Tokenizers 0.11.6