Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming
Abstract
Recent advances in language models have achieved significant progress. GPT-4o, as a new milestone, has enabled real-time conversations with humans, demonstrating near-human natural fluency. Such human-computer interaction necessitates models with the capability to perform reasoning directly with the audio modality and generate output in streaming. However, this remains beyond the reach of current academic models, as they typically depend on extra TTS systems for speech synthesis, resulting in undesirable latency. This paper introduces the Mini-Omni, an audio-based end-to-end conversational model, capable of real-time speech interaction. To achieve this capability, we propose a text-instructed speech generation method, along with batch-parallel strategies during inference to further boost the performance. Our method also helps to retain the original model's language capabilities with minimal degradation, enabling other works to establish real-time interaction capabilities. We call this training method "Any Model Can Talk". We also introduce the VoiceAssistant-400K dataset to fine-tune models optimized for speech output. To our best knowledge, Mini-Omni is the first fully end-to-end, open-source model for real-time speech interaction, offering valuable potential for future research.
Community
This is impressive
Hi, I'm Changqiao Wu, author of the paper, thanks for you interest and recommandation,
the code and demo: https://github.com/gpt-omni/mini-omni/tree/main
hf model: https://huggingface.co/gpt-omni/mini-omni
hf space: https://huggingface.co/spaces/gpt-omni/mini-omni
streamlit interaction demo:
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation (2024)
- Language Model Can Listen While Speaking (2024)
- VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling (2024)
- dMel: Speech Tokenization made Simple (2024)
- Generative Expressive Conversational Speech Synthesis (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
how can I recreate this video with code?
Models citing this paper 2
Datasets citing this paper 0
No dataset linking this paper