FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Kaituo, Jia, Yan, Huang, Kai, Chen, Junjie, Li, Wenpeng, Liu, Kun, Xie, Feng-Long, Tang, Xu, Hu, Yao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915853508804608
author Xu, Kaituo
Jia, Yan
Huang, Kai
Chen, Junjie
Li, Wenpeng
Liu, Kun
Xie, Feng-Long
Tang, Xu
Hu, Yao
author_facet Xu, Kaituo
Jia, Yan
Huang, Kai
Chen, Junjie
Li, Wenpeng
Liu, Kun
Xie, Feng-Long
Tang, Xu
Hu, Yao
contents We present FireRedASR2S, a state-of-the-art industrial-grade all-in-one automatic speech recognition (ASR) system. It integrates four modules in a unified pipeline: ASR, Voice Activity Detection (VAD), Spoken Language Identification (LID), and Punctuation Prediction (Punc). All modules achieve SOTA performance on the evaluated benchmarks: FireRedASR2: An ASR module with two variants, FireRedASR2-LLM (8B+ parameters) and FireRedASR2-AED (1B+ parameters), supporting speech and singing transcription for Mandarin, Chinese dialects and accents, English, and code-switching. Compared to FireRedASR, FireRedASR2 delivers improved recognition accuracy and broader dialect and accent coverage. FireRedASR2-LLM achieves 2.89% average CER on 4 public Mandarin benchmarks and 11.55% on 19 public Chinese dialects and accents benchmarks, outperforming competitive baselines including Doubao-ASR, Qwen3-ASR, and Fun-ASR. FireRedVAD: An ultra-lightweight module (0.6M parameters) based on the Deep Feedforward Sequential Memory Network (DFSMN), supporting streaming VAD, non-streaming VAD, and multi-label VAD (mVAD). On the FLEURS-VAD-102 benchmark, it achieves 97.57% frame-level F1 and 99.60% AUC-ROC, outperforming Silero-VAD, TEN-VAD, FunASR-VAD, and WebRTC-VAD. FireRedLID: An Encoder-Decoder LID module supporting 100+ languages and 20+ Chinese dialects and accents. On FLEURS (82 languages), it achieves 97.18% utterance-level accuracy, outperforming Whisper and SpeechBrain. FireRedPunc: A BERT-style punctuation prediction module for Chinese and English. On multi-domain benchmarks, it achieves 78.90% average F1, outperforming FunASR-Punc (62.77%). To advance research in speech processing, we release model weights and code at https://github.com/FireRedTeam/FireRedASR2S.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10420
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System
Xu, Kaituo
Jia, Yan
Huang, Kai
Chen, Junjie
Li, Wenpeng
Liu, Kun
Xie, Feng-Long
Tang, Xu
Hu, Yao
Audio and Speech Processing
Sound
We present FireRedASR2S, a state-of-the-art industrial-grade all-in-one automatic speech recognition (ASR) system. It integrates four modules in a unified pipeline: ASR, Voice Activity Detection (VAD), Spoken Language Identification (LID), and Punctuation Prediction (Punc). All modules achieve SOTA performance on the evaluated benchmarks: FireRedASR2: An ASR module with two variants, FireRedASR2-LLM (8B+ parameters) and FireRedASR2-AED (1B+ parameters), supporting speech and singing transcription for Mandarin, Chinese dialects and accents, English, and code-switching. Compared to FireRedASR, FireRedASR2 delivers improved recognition accuracy and broader dialect and accent coverage. FireRedASR2-LLM achieves 2.89% average CER on 4 public Mandarin benchmarks and 11.55% on 19 public Chinese dialects and accents benchmarks, outperforming competitive baselines including Doubao-ASR, Qwen3-ASR, and Fun-ASR. FireRedVAD: An ultra-lightweight module (0.6M parameters) based on the Deep Feedforward Sequential Memory Network (DFSMN), supporting streaming VAD, non-streaming VAD, and multi-label VAD (mVAD). On the FLEURS-VAD-102 benchmark, it achieves 97.57% frame-level F1 and 99.60% AUC-ROC, outperforming Silero-VAD, TEN-VAD, FunASR-VAD, and WebRTC-VAD. FireRedLID: An Encoder-Decoder LID module supporting 100+ languages and 20+ Chinese dialects and accents. On FLEURS (82 languages), it achieves 97.18% utterance-level accuracy, outperforming Whisper and SpeechBrain. FireRedPunc: A BERT-style punctuation prediction module for Chinese and English. On multi-domain benchmarks, it achieves 78.90% average F1, outperforming FunASR-Punc (62.77%). To advance research in speech processing, we release model weights and code at https://github.com/FireRedTeam/FireRedASR2S.
title FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2603.10420