A collection of experimental scripts for playing with "generative ai"
use whisper2me.py to speak or text2me.py to message your computer directly and have it respond to you with:
- Answers to questions
- Interesting conversation
- Text completion
- code answers and examples
- Image generation
- Music Generation
wip... more to come
Concepts, code and inspiration built on the shoulders of these giants:
Whisper from openai was used for STT
'Riffusion' [created by Seth Forsgren and Hayk Martiros ](https://huggingface.co/riffusion/riffusion-model-v1
You can use the Riffusion model directly, or try the Riffusion web app(https://www.riffusion.com/).
'Riffusion demo' https://huggingface.co/spaces/anzorq/riffusion-demo
The Riffusion model was created by fine-tuning the Stable-Diffusion-v1-5 checkpoint.
Image generation is done with either OpenAI Dalle (if you have an api key) or Stable Diffusion
OpenAI Dalle: https://openai.com/blog/dall-e/
Stable Diffusion: https://huggingface.co/blog/stable-diffusion
'Whisper Mic' https://github.com/mallorbc/whisper_mic
'Coqui.ai TTS' https://tts.readthedocs.io/en/latest/index.html