e-johnstonn / wingmanai Goto Github PK

Is this similar project?

If functions match, suggest to add it in readme section for "similar project" list

https://github.com/SevaSk/ecoute

This project is incredible. I love it.

I've been trying to figure one part out unsuccessfully, as I'm rather new at coding.
Is there a way to also save a second transcript (i.e., transcript_full.txt) using an append feature. I imagine this would be easy for someone more skilled, but my attempts have failed me. I also seem to not be having luck with the chat feature.

My other general ideas:
2. implement a third tab with a summarize button, which summarizes the transcript full transcript back a set amount.
3. ability to hit enter to send a query to the model.
4. local embedding database for entirely offline use.
5. ability to persist the window.

Can soundstrom & wingmanAI integration helps to users?

https://github.com/lucidrains/soundstorm-pytorch

Looks like a useful project! Would it be possible to support macOS in the future?

The environment I installed is absolutely correct

I tried to test my default microphone device on a microphone testing website, and I can see that it is normal and there are noises

But the program does not seem to collect my voice, how to solve it

• Support for other languages?
• Translation & Transliteration in other languages can be supported?

Seva just updated Ecoute with API calls to Whisper (instead of local ones with CUDA GPU), which made the application more faster.

Could you merge the latest Ecoute?

Thanks!