bkh6722 commited on
Commit
24df001
·
1 Parent(s): 5e1cf81

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -1
README.md CHANGED
@@ -1,10 +1,20 @@
 
 
 
 
 
 
 
1
 
2
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
3
  should probably proofread and complete it, then remove this comment. -->
4
 
5
  # bach-arb
6
 
7
- This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
 
 
 
8
 
9
  ## Model description
10
 
@@ -35,6 +45,28 @@ The following hyperparameters were used during training:
35
  - num_epochs: 320
36
  - mixed_precision_training: Native AMP
37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  ### Framework versions
39
 
40
  - Transformers 4.11.3
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ name: bach-arb
7
+ ---
8
 
9
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
  should probably proofread and complete it, then remove this comment. -->
11
 
12
  # bach-arb
13
 
14
+ This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-german](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-german) on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 8.2433
17
+ - Wer: 1.2104
18
 
19
  ## Model description
20
 
 
45
  - num_epochs: 320
46
  - mixed_precision_training: Native AMP
47
 
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 6.8552 | 20.0 | 100 | 3.0998 | 1.0 |
53
+ | 2.7154 | 40.0 | 200 | 3.1360 | 1.0029 |
54
+ | 1.778 | 60.0 | 300 | 3.9075 | 1.0173 |
55
+ | 0.8588 | 80.0 | 400 | 5.1158 | 1.1354 |
56
+ | 0.4147 | 100.0 | 500 | 6.1905 | 1.0403 |
57
+ | 0.21 | 120.0 | 600 | 6.7319 | 1.3026 |
58
+ | 0.1141 | 140.0 | 700 | 6.8747 | 1.1556 |
59
+ | 0.0713 | 160.0 | 800 | 7.4069 | 1.2911 |
60
+ | 0.0544 | 180.0 | 900 | 7.2074 | 1.1729 |
61
+ | 0.0427 | 200.0 | 1000 | 7.7323 | 1.2219 |
62
+ | 0.0325 | 220.0 | 1100 | 8.0445 | 1.1354 |
63
+ | 0.0257 | 240.0 | 1200 | 7.8804 | 1.1210 |
64
+ | 0.0194 | 260.0 | 1300 | 8.1589 | 1.1470 |
65
+ | 0.0164 | 280.0 | 1400 | 8.2274 | 1.1470 |
66
+ | 0.0132 | 300.0 | 1500 | 8.2207 | 1.1527 |
67
+ | 0.0124 | 320.0 | 1600 | 8.2433 | 1.2104 |
68
+
69
+
70
  ### Framework versions
71
 
72
  - Transformers 4.11.3