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
Is Spanish support on the roadmap?
#12
by iberdrolaaicenter - opened
We would like to know if adding Spanish language is considered any time soon :)
For this particular model architecture, the focus for the next version is intelligence and robustness. Multilingual support such as adding Spanish language is on our list as well. Thanks for the feedback!
royrajarshi changed discussion status to closed
@royrajarshi Thank you for your response. Do you already have a planned date for the Spanish rollout?
@royrajarshi — I'm also interested in the Spanish rollout. Please provide an update when possible. Thank you.
is it possible for us to add another language support like Turkish.