- `translate` functionality added - fix word timestamp bug (words no longer have consecutive timestamps)
3.1.0
- 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
3.0.2
torch2.0, python3.10
3.0.1
- fix pickling error (set num_workers=0) to perform dataloading iwth main process - add basic diarization - pad language detection if less than 30s