[STT] Add support for OpenAI's whisper

NaomiProject / Naomi

The Naomi Project is an open source, technology agnostic platform for developing always-on, voice-controlled applications!

https://projectnaomi.com/

MIT License

242 stars 47 forks source link

[STT] Add support for OpenAI's whisper #380

Open TristanWasTaken opened 1 year ago

TristanWasTaken commented 1 year ago

Add support for OpenAI's Whisper.

Detailed Description

OpenAI published their own STT engine, whisper, some time ago, with quite recently publishing a larger 10GB model file with 1550 M parameters. Whisper currently supports 57 languages.

Context

I'm using Whisper for personal projects.

Possible Implementation

A new STT plugin.

aaronchantrill commented 1 year ago

How are you using Whisper in your own projects? We usually need to be able to customize the dictionary somewhat, usually because of people, place, album, song, etc. names that do not appear in the default dictionary. Do you have any experience with that?

Thanks!