2 pages tagged across the site.
Building the Video Translator , the assumption going in was that OpenAI Whisper’s larger model would transcribe more accurately. In practice, on clips with loud background music, the turbo model did noticeably better than large — it seems to tolerate messy audio better rather than just being a faster, lower-quality option. Separating vocals from background music first (with demucs) didn’t help as much as expected either; Whisper handled the mixed track better on its own. Worth trying turbo first rather than assuming bigger is more accurate.
A local AI dubbing pipeline that transcribes a video's audio, translates it, and re-synthesizes speech in the target language using open-source models.