bangla-speech-processing
/

BanglaASR

Automatic Speech Recognition

Model card Files Files and versions

saiful9379 commited on Jul 2, 2023

Commit

13f55f8

·

1 Parent(s): fb730d7

update readme

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -13,9 +13,9 @@ widget:
 pipeline_tag: automatic-speech-recognition
 ---
-Bangla ASR[Whisper BanglaASR] model which was trained Bangla Mozilla Common Voice Dataset. This is Fine-tuning Whisper for Bangla mozilla common voice dataset.
 For training Bangla ASR model here used 40k traning and 7k Validation around 400 hours data. We trained 12000 steps this model and get word
-error rate 4.58%.
 ```py

 pipeline_tag: automatic-speech-recognition
 ---
+Bangla ASR model which was trained Bangla Mozilla Common Voice Dataset. This is Fine-tuning Whisper for Bangla mozilla common voice dataset.
 For training Bangla ASR model here used 40k traning and 7k Validation around 400 hours data. We trained 12000 steps this model and get word
+error rate 4.58%. This model was fine-tune whisper small[244 M] model.
 ```py