Instructions to use nu-dialogue/j-moshi-ext with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use nu-dialogue/j-moshi-ext with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "nu-dialogue/j-moshi-ext" # 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("nu-dialogue/j-moshi-ext") # 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
Commit History
Add English version 11b6f1f verified
Add library_name fd9d60c verified
Atsumoto Ohashi commited on
Fix base_model (moshika -> moshiko) 60ac25a verified
Atsumoto Ohashi commited on
Create README.md 54e7a84 verified
Atsumoto Ohashi commited on
Upload moshi lm 98c8371 verified
Atsumoto Ohashi commited on
Upload tokenizer-e351c8d8-checkpoint125.safetensors with huggingface_hub dfef6a8 verified
Atsumoto Ohashi commited on
Upload tokenizer_spm_32k_3.model with huggingface_hub 63f1c97 verified
Atsumoto Ohashi commited on
initial commit e5a216f verified
Atsumoto Ohashi commited on