Llama-3.1-8B-Omni

🦙🎧 LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Authors: Qingkai Fang, Shoutao Guo, Yan Zhou, Zhengrui Ma, Shaolei Zhang, Yang Feng*

[Paper] [Model] [Code]

LLaMA-Omni is a speech-language model built upon Llama-3.1-8B-Instruct. It supports low-latency and high-quality speech interactions, simultaneously generating both text and speech responses based on speech instructions.

💡 Highlights

• 💪 Built on Llama-3.1-8B-Instruct, ensuring high-quality responses.

• 🚀 Low-latency speech interaction with a latency as low as 226ms.

• 🎧 Simultaneous generation of both text and speech responses.

• ♻️ Trained in less than 3 days using just 4 GPUs.

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/65b7573482d384513443875e/dr4XWUxzuVQ52lBuzNBTt.mp4"></video>

Install

1. Clone this repository.

git clone https://github.com/ictnlp/LLaMA-Omni
cd LLaMA-Omni

1. Install packages.

conda create -n llama-omni python=3.10
conda activate llama-omni
pip install pip==24.0
pip install -e .

1. Install fairseq.

git clone https://github.com/pytorch/fairseq
cd fairseq
pip install -e . --no-build-isolation

1. Install flash-attention.

pip install flash-attn --no-build-isolation

Quick Start

1. Download the Llama-3.1-8B-Omni model from 🤗Huggingface.

2. Download the Whisper-large-v3 model.

import whisper
model = whisper.load_model("large-v3", download_root="models/speech_encoder/")

1. Download the unit-based HiFi-GAN vocoder.

wget https://dl.fbaipublicfiles.com/fairseq/speech_to_speech/vocoder/code_hifigan/mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj/g_00500000 -P vocoder/
wget https://dl.fbaipublicfiles.com/fairseq/speech_to_speech/vocoder/code_hifigan/mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj/config.json -P vocoder/

Gradio Demo

1. Launch a controller.

python -m omni_speech.serve.controller --host 0.0.0.0 --port 10000

1. Launch a gradio web server.

python -m omni_speech.serve.gradio_web_server --controller http://localhost:10000 --port 8000 --model-list-mode reload --vocoder vocoder/g_00500000 --vocoder-cfg vocoder/config.json

1. Launch a model worker.

python -m omni_speech.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path Llama-3.1-8B-Omni --model-name Llama-3.1-8B-Omni --s2s

1. Visit http://localhost:8000/ and interact with LLaMA-3.1-8B-Omni!

Note: Due to the instability of streaming audio playback in Gradio, we have only implemented streaming audio synthesis without enabling autoplay. If you have a good solution, feel free to submit a PR. Thanks!

Local Inference

To run inference locally, please organize the speech instruction files according to the format in the omni_speech/infer/examples directory, then refer to the following script.

bash omni_speech/infer/run.sh omni_speech/infer/examples

LICENSE

Our code is released under the Apache-2.0 License. Our model is intended for academic research purposes only and may NOT be used for commercial purposes.

You are free to use, modify, and distribute this model in academic settings, provided that the following conditions are met:

• Non-commercial use: The model may not be used for any commercial purposes.
• Citation: If you use this model in your research, please cite the original work.

Commercial Use Restriction

For any commercial use inquiries or to obtain a commercial license, please contact [email protected].

Acknowledgements

• LLaVA: The codebase we built upon.
• SLAM-LLM: We borrow some code about speech encoder and speech adaptor.

Citation

If you have any questions, please feel free to submit an issue or contact [email protected].

If our work is useful for you, please cite as:

@article{fang-etal-2024-llama-omni,
  title={LLaMA-Omni: Seamless Speech Interaction with Large Language Models},
  author={Fang, Qingkai and Guo, Shoutao and Zhou, Yan and Ma, Zhengrui and Zhang, Shaolei and Feng, Yang},
  journal={arXiv preprint arXiv:2409.06666},
  year={2024}
}