WhisperX Versions Save

• translate functionality added
• fix word timestamp bug (words no longer have consecutive timestamps)

• 70x real time transcription, <8GB gpu memory requirement ⚡️⚡️
• each transcript segment is a sentence (using nltk.sent_tokenize)
• diarization now assigned per sentence (and outputted to srt)
• clean up on alignment logic

torch2.0, python3.10

• fix pickling error (set num_workers=0) to perform dataloading iwth main process
• add basic diarization
• pad language detection if less than 30s

batched inference with faster-whisper backend