FireRedASR2S：业界领先的工业级一体化自动语音识别系统

摘要

我们推出FireRedASR2S，这是一款工业级一体化自动语音识别（ASR）系统。该系统集成了四大模块：语音识别（ASR）、语音活动检测（VAD）、口语语言识别（LID）及标点预测（Punc）。所有模块在评测基准中均达到业界领先水平：FireRedASR2语音识别模块提供两种变体——FireRedASR2-LLM（80亿+参数）与FireRedASR2-AED（10亿+参数），支持普通话、汉语方言与口音、英语及中英混杂场景的语音与歌声转写。相较前代FireRedASR，新版在识别准确率与方言覆盖广度上显著提升。FireRedASR2-LLM在4个普通话公开基准上平均字错误率（CER）达2.89%，在19个汉语方言与口音基准上达11.55%，性能超越豆包-ASR、通义千问-ASR、Fun-ASR等竞品。FireRedVAD模块基于深度前馈序列记忆网络（DFSMN），参数量仅60万，支持流式/非流式VAD及多标签VAD（mVAD）。在FLEURS-VAD-102基准上取得97.57%帧级F1值与99.60% AUC-ROC，优于Silero-VAD、TEN-VAD、FunASR-VAD及WebRTC-VAD。FireRedLID模块采用编码器-解码器架构，支持100+语言与20+汉语方言及口音识别，在FLEURS（82种语言）测试中语句级准确率达97.18%，超越Whisper与SpeechBrain。FireRedPunc模块采用BERT风格架构，支持中英文标点预测，在多领域基准上平均F1值达78.90%，显著优于FunASR-Punc（62.77%）。为促进语音处理研究，我们已在https://github.com/FireRedTeam/FireRedASR2S开源模型权重与代码。

English

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.

FireRedASR2S：业界领先的工业级一体化自动语音识别系统

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

摘要

Support