- SpectroStream for Audio Codec
- MusicCoCa for Audio Emebdding
- Transformer LLM for predicting next audio token with given token and embeddings of previous 10 seconds context window
# With GPU support: pip install 'git+https://github.com/magenta/magenta-realtime#egg=magenta_rt[gpu]' # With TPU support: pip install 'git+https://github.com/magenta/magenta-realtime#egg=magenta_rt[tpu]' # CPU only pip install 'git+https://github.com/magenta/magenta-realtime'
google/magenta-realtime · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
https://huggingface.co/google/magenta-realtime

Seonglae Cho