boumehdi commited on
Commit
f88d431
1 Parent(s): 8e931b1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -17,20 +17,20 @@ model-index:
17
  metrics:
18
  - name: Test WER
19
  type: wer
20
- value: 0.162435
21
  ---
22
  # Wav2Vec2-Large-XLSR-53-Moroccan-Darija
23
 
24
  **wav2vec2-large-xlsr-53 new model**
25
 
26
- - Fine-tuned on 36 hours of labeled Darija Audios extracted from MDVC corpus which contains more than 1000 hours of Moroccan Darija "ary".
27
  - Fine-tuning is ongoing 24/7 to enhance accuracy.
28
  - We are consistently adding data to the model every day (We prefer not to add all MDVC Corpus at once as we are trying to standardize more and more the way we write this language).
29
 
30
  <table><thead><tr><th><strong>Training Loss</strong></th> <th><strong>Validation</strong></th> <th><strong>Loss Wer</strong></th></tr></thead> <tbody><tr>
31
- <td>0.026800</td>
32
- <td>0.238950</td>
33
- <td>0.162435</td>
34
  </tr> </tbody></table>
35
 
36
  ## Usage
 
17
  metrics:
18
  - name: Test WER
19
  type: wer
20
+ value: 0.154781
21
  ---
22
  # Wav2Vec2-Large-XLSR-53-Moroccan-Darija
23
 
24
  **wav2vec2-large-xlsr-53 new model**
25
 
26
+ - Fine-tuned on 37 hours of labeled Darija Audios extracted from MDVC corpus which contains more than 1000 hours of Moroccan Darija "ary".
27
  - Fine-tuning is ongoing 24/7 to enhance accuracy.
28
  - We are consistently adding data to the model every day (We prefer not to add all MDVC Corpus at once as we are trying to standardize more and more the way we write this language).
29
 
30
  <table><thead><tr><th><strong>Training Loss</strong></th> <th><strong>Validation</strong></th> <th><strong>Loss Wer</strong></th></tr></thead> <tbody><tr>
31
+ <td>0.026100</td>
32
+ <td>0.231592</td>
33
+ <td>0.154781</td>
34
  </tr> </tbody></table>
35
 
36
  ## Usage