Update README.md
Browse files
README.md
CHANGED
@@ -43,6 +43,10 @@ It achieves the following results on the evaluation set:
|
|
43 |
- WER: 38.6207
|
44 |
- CER: 7.3256
|
45 |
|
|
|
|
|
|
|
|
|
46 |
## Model description
|
47 |
|
48 |
More information needed
|
|
|
43 |
- WER: 38.6207
|
44 |
- CER: 7.3256
|
45 |
|
46 |
+
Note that Whisper's normalization has major issues for languages like Malayalam, so the above scores are evaluated without using normalization.
|
47 |
+
With normalization (for a fair comparison with other models on this platform), the results are instead:
|
48 |
+
- WER: 11.49
|
49 |
+
|
50 |
## Model description
|
51 |
|
52 |
More information needed
|