lucas-meyer commited on
Commit
3fbeda9
1 Parent(s): 3edcbfa

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -19
README.md CHANGED
@@ -14,24 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # xls-r-asr_af-run7
16
 
17
- This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
18
- It achieves the following results on the evaluation set:
19
- - Loss: 0.5110
20
- - Wer: 0.3826
21
-
22
- ## Model description
23
-
24
- More information needed
25
-
26
- ## Intended uses & limitations
27
-
28
- More information needed
29
-
30
- ## Training and evaluation data
31
-
32
- More information needed
33
-
34
- ## Training procedure
35
 
36
  ### Training hyperparameters
37
 
@@ -50,7 +36,7 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
  | 5.3239 | 1.47 | 250 | 2.9818 | 1.0 |
56
  | 2.0745 | 2.93 | 500 | 0.9755 | 0.7501 |
 
14
 
15
  # xls-r-asr_af-run7
16
 
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the asr_af dataset.
18
+ It achieves the following results:
19
+ - Wer (Validation): 41.83%
20
+ - Wer (Test): 42.12%
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
  ### Training hyperparameters
23
 
 
36
 
37
  ### Training results
38
 
39
+ | Training Loss | Epoch | Step | Validation Loss | Wer (Train) |
40
  |:-------------:|:-----:|:----:|:---------------:|:------:|
41
  | 5.3239 | 1.47 | 250 | 2.9818 | 1.0 |
42
  | 2.0745 | 2.93 | 500 | 0.9755 | 0.7501 |