🤗 Kimi-Audio-7B | 🤗 Kimi-Audio-7B-Instruct | 📑 Paper
We present Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation. This repository hosts the model checkpoints for Kimi-Audio-7B.
Kimi-Audio is designed as a universal audio foundation model capable of handling a wide variety of audio processing tasks within a single unified framework. Key features include:
For more details, please refer to our GitHub Repository and Technical Report.
Kimi-Audio-7B is a base model without fine-tuning. So it cannot be used directly. The base model is quite flexible, you can fine-tune it on any possible downstream tasks.
If you are looking for an out-of-the-box model, please refer to Kimi-Audio-7B-Instruct.
If you find Kimi-Audio useful in your research or applications, please cite our technical report:
@misc{kimi_audio_2024,
title={Kimi-Audio Technical Report},
author={Kimi Team},
year={2024},
eprint={arXiv:placeholder},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
The model is based and modified from Qwen 2.5-7B. Code derived from Qwen2.5-7B is licensed under the Apache 2.0 License. Other parts of the code are licensed under the MIT License.
audio_detokenizer/model.pt 19 GBmodel-36-of-36.safetensors 3.6 GBwhisper-large-v3/model.safetensors 3.1 GBvocoder/model.pt 965 MBmodel-29-of-35.safetensors 466 MBmodel-30-of-35.safetensors 466 MBmodel-31-of-35.safetensors 466 MBmodel-32-of-35.safetensors 466 MBmodel-33-of-35.safetensors 466 MBmodel-34-of-35.safetensors 466 MBmodel-11-of-35.safetensors 466 MBmodel-12-of-35.safetensors 466 MBmodel-13-of-35.safetensors 466 MBmodel-14-of-35.safetensors 466 MBmodel-15-of-35.safetensors 466 MBmodel-16-of-35.safetensors 466 MBmodel-17-of-35.safetensors 466 MBmodel-18-of-35.safetensors 466 MBmodel-19-of-35.safetensors 466 MBmodel-20-of-35.safetensors 466 MBmodel-21-of-35.safetensors 466 MBmodel-22-of-35.safetensors 466 MBmodel-23-of-35.safetensors 466 MBmodel-24-of-35.safetensors 466 MBmodel-25-of-35.safetensors 466 MBmodel-26-of-35.safetensors 466 MBmodel-27-of-35.safetensors 466 MBmodel-28-of-35.safetensors 466 MBmodel-1-of-35.safetensors 466 MBmodel-10-of-35.safetensors 466 MBmodel-2-of-35.safetensors 466 MBmodel-3-of-35.safetensors 466 MBmodel-4-of-35.safetensors 466 MBmodel-5-of-35.safetensors 466 MBmodel-6-of-35.safetensors 466 MBmodel-7-of-35.safetensors 466 MBmodel-8-of-35.safetensors 466 MBmodel-9-of-35.safetensors 466 MBmodel-35-of-35.safetensors 62 MBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo moonshotai/Kimi-Audio-7B ./model-folder