again

again

try to fix cuda error

try to fix cuda error

try fallback requirements.txt

restore to whisper

ctranslate2

switch transcribing back to faster_whisper

numpy>=1.24.0 again

switch to whisperX

add upload

Implement audio preprocessing and speaker diarization enhancements in WhisperTranscriber. Introduce methods for audio chunk preparation, VAD-based trimming, and speaker embedding extraction. Update process_audio methods to utilize task JSON for improved workflow and metadata handling. Add webrtcvad dependency for voice activity detection.

requirements.txt

requirements.txt

update numpy version constraint to be less than 1.24.0 in requirements.txt

requirements

requirements

nvidia-cudnn-cu12

nvidia-cudnn-cu12

fast whisper

update Gradio SDK version to 5.0.1 in README and requirements

update requirements.txt

update code

update requirements.txt

remove source param

update requirements.txt

update requirements.txt

init