Audio-to-Audio
Moshi
Safetensors
Hindi
speech-to-speech
hindi
conversational-ai
audio
full-duplex
duplex-dialogue
indian-languages
Instructions to use JoshTalksAI/Human-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use JoshTalksAI/Human-1 with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "JoshTalksAI/Human-1" # 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("JoshTalksAI/Human-1") # 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
- Xet hash:
- 0af5cf2663704d8fcbdc210a6121680d5ce7343dea42b68ccbb617b272fb848d
- Size of remote file:
- 1.08 MB
- SHA256:
- a05524805f181f74520be13b407cb00bcea3872398bcd0058d75e40c6bfc13c2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.