Hugging Face's logo

Finnish-NLP
/
wav2vec2-base-fi-voxpopuli-v2-finetuned

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Finnish
wav2vec2
finnish
Generated from Trainer
hf-asr-leaderboard
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
aapot commited on
Commit
586894d
•
1 Parent(s): 055b8c9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-base-fi-voxpopuli-v2-finetuned
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
+ # wav2vec2-base-fi-voxpopuli-v2-finetuned
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-base-fi-voxpopuli-v2](https://huggingface.co/facebook/wav2vec2-base-fi-voxpopuli-v2) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.1316
18
+ - Wer: 0.1498
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 64
39
+ - eval_batch_size: 64
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 10
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
+ | 1.575 | 0.33 | 500 | 0.7454 | 0.7048 |
52
+ | 0.5838 | 0.66 | 1000 | 0.2377 | 0.2608 |
53
+ | 0.5692 | 1.0 | 1500 | 0.2014 | 0.2244 |
54
+ | 0.5112 | 1.33 | 2000 | 0.1885 | 0.2013 |
55
+ | 0.4857 | 1.66 | 2500 | 0.1881 | 0.2120 |
56
+ | 0.4821 | 1.99 | 3000 | 0.1603 | 0.1894 |
57
+ | 0.4531 | 2.32 | 3500 | 0.1594 | 0.1865 |
58
+ | 0.4411 | 2.65 | 4000 | 0.1641 | 0.1874 |
59
+ | 0.4437 | 2.99 | 4500 | 0.1545 | 0.1874 |
60
+ | 0.4191 | 3.32 | 5000 | 0.1565 | 0.1770 |
61
+ | 0.4158 | 3.65 | 5500 | 0.1696 | 0.1867 |
62
+ | 0.4032 | 3.98 | 6000 | 0.1561 | 0.1746 |
63
+ | 0.4003 | 4.31 | 6500 | 0.1432 | 0.1749 |
64
+ | 0.4059 | 4.64 | 7000 | 0.1390 | 0.1690 |
65
+ | 0.4019 | 4.98 | 7500 | 0.1291 | 0.1646 |
66
+ | 0.3811 | 5.31 | 8000 | 0.1485 | 0.1755 |
67
+ | 0.3955 | 5.64 | 8500 | 0.1351 | 0.1659 |
68
+ | 0.3562 | 5.97 | 9000 | 0.1328 | 0.1614 |
69
+ | 0.3646 | 6.3 | 9500 | 0.1329 | 0.1584 |
70
+ | 0.351 | 6.64 | 10000 | 0.1342 | 0.1554 |
71
+ | 0.3408 | 6.97 | 10500 | 0.1422 | 0.1509 |
72
+ | 0.3562 | 7.3 | 11000 | 0.1309 | 0.1528 |
73
+ | 0.3335 | 7.63 | 11500 | 0.1305 | 0.1506 |
74
+ | 0.3491 | 7.96 | 12000 | 0.1365 | 0.1560 |
75
+ | 0.3538 | 8.29 | 12500 | 0.1293 | 0.1512 |
76
+ | 0.3338 | 8.63 | 13000 | 0.1328 | 0.1511 |
77
+ | 0.3509 | 8.96 | 13500 | 0.1304 | 0.1520 |
78
+ | 0.3431 | 9.29 | 14000 | 0.1360 | 0.1517 |
79
+ | 0.3309 | 9.62 | 14500 | 0.1328 | 0.1514 |
80
+ | 0.3252 | 9.95 | 15000 | 0.1316 | 0.1498 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.19.1
86
+ - Pytorch 1.11.0+cu102
87
+ - Datasets 2.2.1
88
+ - Tokenizers 0.11.0