You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

SoviaMate-Codec

Audio codec model for the SoviaMate speech AI assistant.

Model Description

SoviaMate-Codec is a neural audio codec designed for high-quality speech compression and reconstruction. It serves as the audio backbone for the SoviaMate spoken dialogue system.

Files

File	Description	Size
`audio_codec.ckpt`	Base audio codec model	~766 MB
`audio_codec_asr.ckpt`	Audio codec with ASR features	~974 MB

Usage

Download

# Using HuggingFace CLI
hf download samson-labs/SoviaMate-Codec --local-dir models/codec

# Or using Python
from huggingface_hub import hf_hub_download

hf_hub_download(repo_id="samson-labs/SoviaMate-Codec", filename="audio_codec.ckpt", local_dir="models/codec")

Integration

See the SoviaMate repository for full usage instructions.

License

This model is released under the Apache License 2.0.

Citation

@misc{soviamate2024,
  title={SoviaMate: AI-Powered Speech Assistant},
  author={Samson Voice},
  year={2024},
  url={https://github.com/samson-voice/SoviaMate}
}

Downloads last month: -; Downloads are not tracked for this model. How to track