Instructions to use nvidia/personaplex-7b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use nvidia/personaplex-7b-v1 with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "nvidia/personaplex-7b-v1" # 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("nvidia/personaplex-7b-v1") # 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) - Inference
- Notebooks
- Google Colab
- Kaggle
Can execute function or tools ?
#39
by UrielSalto - opened
How I can adapt it to my use case, just with fine tuning or it's possible implement RAG or any call function ?
same question
You either 1) need finetuning or 2) run an streaming ASR (very lightweight) +LLM in parallel, and feed the results back into the PersonaPlex text channel. We have 2) sort of working internally. But finetuning is the way to do this properly in the future.
royrajarshi changed discussion status to closed