Audio-to-Audio
Moshi
English
speech-to-speech
full-duplex
function-calling
tool-use
voice-agent
realtime
personaplex
low-latency
Instructions to use abhinavpgagi/personaplex-tool-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use abhinavpgagi/personaplex-tool-calling with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "abhinavpgagi/personaplex-tool-calling" # Then open https://localhost:8998 in your browser
# pip install moshi import torch from moshi.models import loaders # Load checkpoint info from HuggingFace checkpoint = loaders.CheckpointInfo.from_hf_repo("abhinavpgagi/personaplex-tool-calling") # Load the Mimi audio codec mimi = checkpoint.get_mimi(device="cuda") mimi.set_num_codebooks(8) # Encode audio (24kHz, mono) wav = torch.randn(1, 1, 24000 * 10) # [batch, channels, samples] with torch.no_grad(): codes = mimi.encode(wav.cuda()) decoded = mimi.decode(codes) - Notebooks
- Google Colab
- Kaggle
Ctrl+K