Instructions to use ayousanz/moshi-persona-stage2-ojousama-2026-07-06 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use ayousanz/moshi-persona-stage2-ojousama-2026-07-06 with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "ayousanz/moshi-persona-stage2-ojousama-2026-07-06" # 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("ayousanz/moshi-persona-stage2-ojousama-2026-07-06") # 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
Path B experiment checkpoint
Fine-tuned from nu-dialogue/j-moshi-ext for Path B research on character persona fine-tuning.
Voice source: amitaro (https://amitaro.net/) - AI 学習可 / 商用可 (要クレジット)
License: CC-BY-NC 4.0 (Moshi inherit) Voice credit: amitaro (https://amitaro.net/)
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support