Transcriber AI – Free, end-to-end machine based transcription with speaker id

Re:Transcriber AI – Free, end-to-end machine based transcrip... by okeysmokey on Monday December 16, 2024 @08:50AM (#42430919)

Is this using Whisper or something else? It looks like the site performs multiple steps on the audio and did a decent job of guessing who was speaking.

[ Parent | on HN ]

Re:Transcriber AI – Free, end-to-end machine based transcrip... by WinH on Monday December 16, 2024 @09:07AM (#42431063)

Yes. We run run Whisper Large V3 (not Turbo) for the speech to text. It still seems to be the best open source model out there for that step. The main challenge we are trying to solve is Speaker Identification, which is a very time consuming process.

[ Parent | on HN ]

Re:Transcriber AI – Free, end-to-end machine based transcrip... by okeysmokey on Monday December 16, 2024 @09:18AM (#42431154)

How are you doing speaker id?

[ Parent | on HN ]

Re:Transcriber AI – Free, end-to-end machine based transcrip... by okeysmokey on Monday December 16, 2024 @09:33AM (#42431296)

It (mostly correctly) ID'd the SCOTUS justices on this one. Pretty cool! https://transcriberai.com/Overview/aa908e33-5680-462a-94ff-6...

[ Parent | on HN ]

Re:Transcriber AI – Free, end-to-end machine based transcrip... by LunaRoot on Monday December 16, 2024 @11:22AM (#42432436)

Really cool! thanks for sharing.

[ Parent | on HN ]