Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/gpt-omni/mini-omni

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.
https://github.com/gpt-omni/mini-omni

Last synced: 1 day ago
JSON representation

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.

Host: GitHub
URL: https://github.com/gpt-omni/mini-omni
Owner: gpt-omni
License: mit
Created: 2024-08-27T10:57:04.000Z (4 months ago)
Default Branch: main
Last Pushed: 2024-11-05T10:19:58.000Z (about 1 month ago)
Last Synced: 2024-11-19T20:02:34.444Z (24 days ago)
Language: Python
Homepage: https://arxiv.org/abs/2408.16725
Size: 11.9 MB
Stars: 3,097
Watchers: 97
Forks: 277
Open Issues: 22
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

ai-game-devtools - Mini-Omni - Omni: Language Models Can Hear, Talk While Thinking in Streaming. Mini-Omni is an open-source multimodel large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities. | [arXiv](https://arxiv.org/abs/2408.16725) | | Speech | (<span id="speech">Speech</span> / <span id="tool">Tool (AI LLM)</span>)

README

# Mini-Omni

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

🤗 Hugging Face | 📖 Github
| 📑 Technical report |
🤗 Datasets

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.

## Updates

- **2024.10:** We released [Mini-Omni2](https://github.com/gpt-omni/mini-omni2) with vision and audio capabilities.
- **2024.09:** Amazing online [interactive gradio demo](https://huggingface.co/spaces/gradio/omni-mini) by 🤗 gradio team.
- **2024.09:** **VoiceAssistant-400K** is uploaded to [Hugging Face](https://huggingface.co/datasets/gpt-omni/VoiceAssistant-400K).

## Features

✅ **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 output** capabilities.

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

## Demo

NOTE: need to unmute first.

https://github.com/user-attachments/assets/03bdde05-9514-4748-b527-003bea57f118

## Install

Create a new conda environment and install the required packages:

```sh
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
```

## Quick start

**Interactive demo**

- start server

NOTE: you need to start the server before running the streamlit or gradio demo with API_URL set to the server address.

```sh
sudo apt-get install ffmpeg
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. For error: `ModuleNotFoundError: No module named 'utils.vad'`, please run `export PYTHONPATH=./` first.

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

- run gradio demo
```sh
API_URL=http://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.

https://github.com/user-attachments/assets/29187680-4c42-47ff-b352-f0ea333496d9

**Local test**

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

## FAQ

**1. Does the model support other languages?**

No, the model is only trained on English. However, as we use whisper as the audio encoder, the model can understand other languages which is supported by whisper (like chinese), but the output is only in English.

**2. What is `post_adapter` in the code? does the open-source version support tts-adapter?**

The `post_adapter` is `tts-adapter` in the model.py, but the open-source version does not support `tts-adapter`.

**3. Error: `ModuleNotFoundError: No module named 'utils.xxxx'`**

Run `export PYTHONPATH=./` first. No need to run `pip install utils`, or just try: `pip uninstall utils`

**4. Error: can not run streamlit in local browser, with remote streamlit server**, issue: https://github.com/gpt-omni/mini-omni/issues/37

You need start streamlit **locally** with PyAudio installed.

## Acknowledgements

- [Qwen2](https://github.com/QwenLM/Qwen2/) as the LLM backbone.
- [litGPT](https://github.com/Lightning-AI/litgpt/) for training and inference.
- [whisper](https://github.com/openai/whisper/) for audio encoding.
- [snac](https://github.com/hubertsiuzdak/snac/) for audio decoding.
- [CosyVoice](https://github.com/FunAudioLLM/CosyVoice) for generating synthetic speech.
- [OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca) and [MOSS](https://github.com/OpenMOSS/MOSS/tree/main) for alignment.

## Star History

[![Star History Chart](https://api.star-history.com/svg?repos=gpt-omni/mini-omni&type=Date)](https://star-history.com/#gpt-omni/mini-omni&Date)