Instructions to use sadmN/moshi-base7b-rag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use sadmN/moshi-base7b-rag with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "sadmN/moshi-base7b-rag" # 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("sadmN/moshi-base7b-rag") # 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
Download tokenizer.model from sadmN/moshi-base7b-rag: direct link, hf CLI and curl.
- Browser
- Download file 553 kB
-
https://huggingface.co/sadmN/moshi-base7b-rag/resolve/main/tokenizer.model
- Command line
-
hf download hf://sadmN/moshi-base7b-rag/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/sadmN/moshi-base7b-rag/resolve/main/tokenizer.model
553 kB
- Xet hash:
- 9075eac7dd1b256d54f975e9863119086637439ef93969bc69abdfcc81b51c56
- Size of remote file:
- 553 kB
- SHA256:
- 8643fea481a8791e9488e6b02687e55b17f9cde650ba9b8f5d6d2318679c9e1d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.