Is there anything like this available to run locally? Our HR dept wants to use something to transcribe interviews but doesn't want to submit data to some random website.

I use whisper and pyannote (https://github.com/m-bain/whisperX), but it is a pain to run locally - I run it on a 4080. This seems to be actually trying to identify the speakers. Not sure what they are doing for that.

seems like running it somewhere secured is the answer, rather than hosting on your own.

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.

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.

How are you doing speaker id?

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

Really cool! thanks for sharing.

speaker identification will be the next breakthrough in AI transcription. Correctly identifying speakers greatly improves the end user's perceived quality of the final transcription product.

Impressed by how accurately this identified and transcribed. Nice work

Thanks, did you try the editor?

Nice work. Like to learn more about this new technology

Nice work. AI will enhance this technology