Qwen2.5-Omni Technical Report

• URL: http://arxiv.org/abs/2503.20215v1
• Date: Wed, 26 Mar 2025 04:17:55 GMT
• Title: Qwen2.5-Omni Technical Report
• Authors: Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, Bin Zhang, Xiong Wang, Yunfei Chu, Junyang Lin,
• Abstract summary: We present an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner.<n>Qwen2.5- Omni achieves state-of-the-art performance on multimodal benchmarks like Omni-Bench.
• Score: 31.033323728153984
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this report, we present Qwen2.5-Omni, an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. To enable the streaming of multimodal information inputs, both audio and visual encoders utilize a block-wise processing approach. To synchronize the timestamps of video inputs with audio, we organize the audio and video sequentially in an interleaved manner and propose a novel position embedding approach, named TMRoPE(Time-aligned Multimodal RoPE). To concurrently generate text and speech while avoiding interference between the two modalities, we propose \textbf{Thinker-Talker} architecture. In this framework, Thinker functions as a large language model tasked with text generation, while Talker is a dual-track autoregressive model that directly utilizes the hidden representations from the Thinker to produce audio tokens as output. Both the Thinker and Talker models are designed to be trained and inferred in an end-to-end manner. For decoding audio tokens in a streaming manner, we introduce a sliding-window DiT that restricts the receptive field, aiming to reduce the initial package delay. Qwen2.5-Omni is comparable with the similarly sized Qwen2.5-VL and outperforms Qwen2-Audio. Furthermore, Qwen2.5-Omni achieves state-of-the-art performance on multimodal benchmarks like Omni-Bench. Notably, Qwen2.5-Omni's performance in end-to-end speech instruction following is comparable to its capabilities with text inputs, as evidenced by benchmarks such as MMLU and GSM8K. As for speech generation, Qwen2.5-Omni's streaming Talker outperforms most existing streaming and non-streaming alternatives in robustness and naturalness.

Related papers

• AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation [24.799628787198397]
  AudioGen- Omni generates high-fidelity audio, speech, and song coherently synchronized with the input video.<n>Joint training paradigm integrates large-scale video-text-audio corpora.<n>Dense frame-level representations are fused using an AdaLN-based joint attention mechanism.<n>With an inference time of 1.91 seconds for 8 seconds of audio, it offers substantial improvements in both efficiency and generality.
  arXiv  Detail & Related papers  (2025-08-01T16:03:57Z)
• VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model [70.25062476543091]
  VITA-Audio is an end-to-end large speech model with fast audio-text token generation.<n>MCTP module efficiently generates multiple audio tokens within a single model forward pass.<n>Four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality.
  arXiv  Detail & Related papers  (2025-05-06T17:59:53Z)
• AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation [41.74261260212531]
  multimodal-to-speech task has gained increasing attention due to its wide range of applications, such as film production, dubbing, and virtual avatars. Existing methods still suffer from limitations in speech intelligibility, audio-video synchronization, speech naturalness, and voice similarity to the reference speaker. We propose AlignDiT, a multimodal Aligned Diffusion Transformer that generates accurate, synchronized, and natural-sounding speech from aligned multimodal inputs.
  arXiv  Detail & Related papers  (2025-04-29T10:56:24Z)
• Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision [50.23246260804145]
  This work proposes an industry-level omni-modal large language model (LLM) pipeline that integrates auditory, visual, and linguistic modalities.<n>Our pipeline consists of three main components: First, a modular framework enabling flexible configuration of various encoder-LLM-decoder architectures.<n>Second, a lightweight training strategy that pre-trains audio-language alignment on the state-of-the-art vision-language model Qwen2.5-VL.<n>Third, an audio synthesis pipeline that generates high-quality audio-text data from diverse real-world scenarios.
  arXiv  Detail & Related papers  (2025-02-26T17:26:36Z)
• SyncSpeech: Low-Latency and Efficient Dual-Stream Text-to-Speech based on Temporal Masked Transformer [68.78023656892319]
  This paper presents a dual-stream text-to-speech (TTS) model, SyncSpeech, capable of receiving streaming text input from upstream models while simultaneously generating streaming speech.<n>SyncSpeech has the following advantages: Low latency, as it begins generating streaming speech upon receiving the second text token; High efficiency, as it decodes all speech tokens corresponding to the each arrived text token in one step.
  arXiv  Detail & Related papers  (2025-02-16T12:14:17Z)
• CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models [74.80386066714229]
  We present an improved streaming speech synthesis model, CosyVoice 2. Specifically, we introduce finite-scalar quantization to improve codebook utilization of speech tokens. We develop a chunk-aware causal flow matching model to support various synthesis scenarios.
  arXiv  Detail & Related papers  (2024-12-13T12:59:39Z)
• Visatronic: A Multimodal Decoder-Only Model for Speech Synthesis [13.702423348269155]
  Video-Text to Speech (VTTS) is a speech generation task conditioned on both its corresponding text and video of talking people.<n>We introduce Visatronic, a unified multimodal decoder-only transformer model that embeds visual, textual, and speech inputs into a shared subspace.<n>We show that Visatronic achieves a 4.5% WER, outperforming prior SOTA methods trained only on LRS3.
  arXiv  Detail & Related papers  (2024-11-26T18:57:29Z)
• A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation [48.84039953531355]
  We propose a novel non-autoregressive generation framework for simultaneous speech translation (NAST-S2X) NAST-S2X integrates speech-to-text and speech-to-speech tasks into a unified end-to-end framework. It achieves high-quality simultaneous interpretation within a delay of less than 3 seconds and provides a 28 times decoding speedup in offline generation.
  arXiv  Detail & Related papers  (2024-06-11T04:25:48Z)
• Cascaded Cross-Modal Transformer for Audio-Textual Classification [30.643750999989233]
  We propose to harness the inherent value of multimodal representations by transcribing speech using automatic speech recognition (ASR) models. We thus obtain an audio-textual (multimodal) representation for each data sample. We were declared the winning solution in the Requests Sub-Challenge of the ACM Multimedia 2023 Computational Paralinguistics Challenge.
  arXiv  Detail & Related papers  (2024-01-15T10:18:08Z)
• Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities [67.89368528234394]
  One of the main challenges of multimodal learning is the need to combine heterogeneous modalities. Video and audio are obtained at much higher rates than text and are roughly aligned in time. Our approach achieves the state-of-the-art on well established multimodal benchmarks, outperforming much larger models.
  arXiv  Detail & Related papers  (2023-11-09T19:15:12Z)
• NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers [90.83782600932567]
  We develop NaturalSpeech 2, a TTS system that leverages a neural audio predictor with residual vectorizers to get the quantized latent vectors. We scale NaturalSpeech 2 to large-scale datasets with 44K hours of speech and singing data and evaluate its voice quality on unseen speakers. NaturalSpeech 2 outperforms previous TTS systems by a large margin in terms of prosody/timbre similarity, synthesis, and voice quality in a zero-shot setting.
  arXiv  Detail & Related papers  (2023-04-18T16:31:59Z)
• MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation [70.74377373885645]
  We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously. MM-Diffusion consists of a sequential multi-modal U-Net for a joint denoising process by design. Experiments show superior results in unconditional audio-video generation, and zero-shot conditional tasks.
  arXiv  Detail & Related papers  (2022-12-19T14:11:52Z)
• Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data [15.658471125219224]
  Multimodal pre-training for audio-and-text has been proven to be effective and has significantly improved the performance of many downstream speech understanding tasks. However, these state-of-the-art pre-training audio-text models work well only when provided with large amount of parallel audio-and-text data. In this paper, we investigate whether it is possible to pre-train an audio-text model with low-resource parallel data.
  arXiv  Detail & Related papers  (2022-04-10T10:25:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.