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
add more language
#4
by mohammadaminyza - opened
Hi
is there any way that i can fine tune arabic or persian in this model?
Not in this model unfortunately. You would have to recreate the methodology from both Moshi (https://arxiv.org/abs/2410.00037) and PersonaPlex (https://huggingface.co/nvidia/personaplex-7b-v1). Plus you would need a Persian or Arabic speech dataset where there are natural conversations between two speakers and the speaker voices are channel separated.
royrajarshi changed discussion status to closed