qxtv
qxtv
Hi curious if this pipeline works if the language I am interested in is not supported by whisperx forced alignment?
I was transcribing an audio file that was about 65 seconds long. However the model kept generating text until about 83s (based on time stamp). Is this an issue with...
"Reduction in Hallucination: Optimized parameters and heuristics to decrease repeated text output or hallucinations." What's the heuristics you've tested?
Just putting it out here. It's a good idea to tune your VadOptions if you are facing some issues with it. Working with non-english inputs, The default value for VadOptions...
Hi may I know which mmcv are you using for this project? I'm running into a problem mmcv.runner not foundl