AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Bringing Whisper and LLaMA to the masses (Changelog Interviews #532)
Changelog Master Feed
How to Diarize Speakers in Python
This is something that we very much desire for our transcripts because we have it already with our human transcribed transcripts. There were like few ideas popping around using whisper in no traditional way to achieve some sort of diarization. It boils down to trying to extract some of the internal results of the computation and try to like classify based on some, let's say, features or I'm not sure really how to properly explain it. For now it seems unlike it. It's a pipe dream. This slow unlikely, at least from my point of view,. maybe if someone fears it out and it pretty works, we could probably have it someday.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode