Let't learn ai voices

We will explore current state of open source solution to generate and recognize voice. Examples of interesting repositories:

https://github.com/openai/whisper
https://github.com/fishaudio/fish-speech
https://github.com/ufal/whisper_streaming

Our goal is to write simple scripts allowing to use these tools and meet new friends interested in this topic.

There is no prepared script or presentations. We can potentially fail doing these tasks, discover problems that was not described in documentation, but it is just part of experience.

Programming language does not matter, we can solve this problem in many languages in the same time.