Files
AudioTranscriberCombine/core/transcribe.py
jadssss 60846e3c6c load the ASR model once per process
- keep WhisperX, align and GigaAM caches process-wide and thread-safe\n- preload the ASR model at the start of the staged stage 3\n- log that the model is loaded once and then reused\n- never clear caches between files, batches or OOM retries
2026-10-28 09:54:06 +03:00

10 KiB