Added some explanations.
Browse files
README.md
CHANGED
@@ -18,7 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# whisper-small-ug
|
20 |
|
21 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 0.3563
|
24 |
- Wer: 26.8793
|
|
|
18 |
|
19 |
# whisper-small-ug
|
20 |
|
21 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset. The model is trained on
|
22 |
+
transcripts written in Uyghur Latin Script via utilising Uzbek Tokeniser , as Uyghur Tokeniser is not included in Whisper. Therefore, the output of the model is
|
23 |
+
in Uyghur Latin Script. To convert the output to the Uyghur Arabic Script, you can use the Uyghur script converter: https://github.com/neouyghur/ScriptConverter4Uyghur
|
24 |
+
|
25 |
+
or you can use online script converter: https://www.yulghun.com/imla/convert.html
|
26 |
+
|
27 |
+
|
28 |
+
|
29 |
It achieves the following results on the evaluation set:
|
30 |
- Loss: 0.3563
|
31 |
- Wer: 26.8793
|