Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,7 @@ pipeline_tag: automatic-speech-recognition
|
|
| 21 |
|
| 22 |
Multilingual Distilwhisper allows for better ASR performance in target languages by adding lightweight CLSR modules on top of whisper-small.
|
| 23 |
These modules are trained on a mix of cross-entropy (ASR) and knowledge distillation losses, where whisper-large-v2 is used as teacher.
|
|
|
|
| 24 |
|
| 25 |
## Inference
|
| 26 |
|
|
|
|
| 21 |
|
| 22 |
Multilingual Distilwhisper allows for better ASR performance in target languages by adding lightweight CLSR modules on top of whisper-small.
|
| 23 |
These modules are trained on a mix of cross-entropy (ASR) and knowledge distillation losses, where whisper-large-v2 is used as teacher.
|
| 24 |
+
More details in the ICASSP 2024 paper: arxiv.org/abs/2311.01070
|
| 25 |
|
| 26 |
## Inference
|
| 27 |
|