Update README.md

README.md

@@ -117,8 +117,10 @@ From my early tests:
 - Much less GPU memory required
 - It seems that performance is on par with the original
 - It seems that this combination is faster than just using the CTranslate2 int8 quantization.
+
 Quantization method TBA. 
-To use this model, use the faster_whisper module as stated in [the original faster-whisper model](https://huggingface.co/Systran/faster-whisper-large-v3) 
+To use this model, use the faster_whisper module as stated in [the original faster-whisper model](https://huggingface.co/Systran/faster-whisper-large-v3). 
+Or use [WhisperX](https://github.com/m-bain/whisperX), this is what I used for my small tests (do not forget to set dtype to int8).
 
 Any benchmark results are appreciated. I probably do not have time to do it myself.
 ## Model Details