Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

🤗 Hugging Face | 📖 Github | 📑 Technical report

Mini-Omni is an open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

✅ Real-time speech-to-speech conversational capabilities. No extra ASR or TTS models required.

✅ Talking while thinking, with the ability to generate text and audio at the same time.

✅ Streaming audio outupt capabilities.

✅ With "Audio-to-Text" and "Audio-to-Audio" batch inference to further boost the performance.

NOTE: need to unmute first.

Create a new conda environment and install the required packages:

conda create -n omni python=3.10
conda activate omni

git clone https://github.com/gpt-omni/mini-omni.git
cd mini-omni
pip install -r requirements.txt

Interactive demo

• start server

conda activate omni
cd mini-omni
python3 server.py --ip '0.0.0.0' --port 60808

• run streamlit demo

NOTE: you need to run streamlit locally with PyAudio installed.

pip install PyAudio==0.2.14
API_URL=https://0.0.0.0:60808/chat streamlit run webui/omni_streamlit.py

• run gradio demo

API_URL=https://0.0.0.0:60808/chat python3 webui/omni_gradio.py

example:

NOTE: need to unmute first. Gradio seems can not play audio stream instantly, so the latency feels a bit longer.

Local test

conda activate omni
cd mini-omni
# test run the preset audio samples and questions
python inference.py

• Qwen2 as the LLM backbone.
• litGPT for training and inference.
• whisper for audio encoding.
• snac for audio decoding.
• CosyVoice for generating synthetic speech.
• OpenOrca and MOSS for alignment.