MiDashengLM: Efficient Audio Understanding with General Audio Captions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dinkel, Heinrich, Li, Gang, Liu, Jizhong, Luan, Jian, Niu, Yadong, Sun, Xingwei, Wang, Tianzi, Xiao, Qiyang, Zhang, Junbo, Zhou, Jiahao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911544797822976
author Dinkel, Heinrich
Li, Gang
Liu, Jizhong
Luan, Jian
Niu, Yadong
Sun, Xingwei
Wang, Tianzi
Xiao, Qiyang
Zhang, Junbo
Zhou, Jiahao
author_facet Dinkel, Heinrich
Li, Gang
Liu, Jizhong
Luan, Jian
Niu, Yadong
Sun, Xingwei
Wang, Tianzi
Xiao, Qiyang
Zhang, Junbo
Zhou, Jiahao
contents Current approaches for large audio language models (LALMs) often rely on closed data sources or proprietary models, limiting their generalization and accessibility. This paper introduces MiDashengLM, a novel open audio-language model designed for efficient and comprehensive audio understanding through the use of general audio captions using our novel ACAVCaps training dataset. MiDashengLM exclusively relies on publicly available pretraining and supervised fine-tuning (SFT) datasets, ensuring full transparency and reproducibility. At its core, MiDashengLM integrates Dasheng, an open-source audio encoder, specifically engineered to process diverse auditory information effectively. Unlike previous works primarily focused on Automatic Speech Recognition (ASR) based audio-text alignment, our strategy centers on general audio captions, fusing speech, sound and music information into one textual representation, enabling a holistic textual representation of complex audio scenes. Lastly, MiDashengLM provides an up to 4x speedup in terms of time-to-first-token (TTFT) and up to 20x higher throughput than comparable models. Checkpoints are available online at https://huggingface.co/mispeech/midashenglm-7b and https://github.com/xiaomi-research/dasheng-lm.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03983
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MiDashengLM: Efficient Audio Understanding with General Audio Captions
Dinkel, Heinrich
Li, Gang
Liu, Jizhong
Luan, Jian
Niu, Yadong
Sun, Xingwei
Wang, Tianzi
Xiao, Qiyang
Zhang, Junbo
Zhou, Jiahao
Sound
Audio and Speech Processing
Current approaches for large audio language models (LALMs) often rely on closed data sources or proprietary models, limiting their generalization and accessibility. This paper introduces MiDashengLM, a novel open audio-language model designed for efficient and comprehensive audio understanding through the use of general audio captions using our novel ACAVCaps training dataset. MiDashengLM exclusively relies on publicly available pretraining and supervised fine-tuning (SFT) datasets, ensuring full transparency and reproducibility. At its core, MiDashengLM integrates Dasheng, an open-source audio encoder, specifically engineered to process diverse auditory information effectively. Unlike previous works primarily focused on Automatic Speech Recognition (ASR) based audio-text alignment, our strategy centers on general audio captions, fusing speech, sound and music information into one textual representation, enabling a holistic textual representation of complex audio scenes. Lastly, MiDashengLM provides an up to 4x speedup in terms of time-to-first-token (TTFT) and up to 20x higher throughput than comparable models. Checkpoints are available online at https://huggingface.co/mispeech/midashenglm-7b and https://github.com/xiaomi-research/dasheng-lm.
title MiDashengLM: Efficient Audio Understanding with General Audio Captions
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2508.03983