一站式语音识别系统，支持中英文多语种语音转写与标点还原。
FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System
- 统一流水线集成四模块：语音识别、语音活动检测、语言识别和标点预测。
- 中文方言识别错误率仅2.89%，多语种语言识别准确率达97.18%。
- 适合工业级语音处理场景，开源模型代码助力研究落地。
我们提出 FireRedASR2S，一个先进的工业级全功能自动语音识别系统。该系统在统一流水线中集成四个模块：语音识别（ASR）、语音活动检测（VAD）、口语语言识别（LID）和标点预测（Punc）。所有模块在评估基准上均达到最先进性能：FireRedASR2 提供两个变体——80亿参数的 FireRedASR2-LLM 和 10亿参数的 FireRedASR2-AED，支持普通话、方言、口音及英语和混合语言的语音与歌唱转录；在4个公开普通话数据集上平均词错误率为2.89%，在19个中文方言与口音数据集上为11.55%，优于 Doubao-ASR、Qwen3-ASR 和 Fun-ASR。FireRedVAD 是基于 DFSMN 构建的超轻量模块（0.6M 参数），支持流式与非流式检测及多标签检测，在 FLEURS-VAD-102 上实现97.57%帧级F1和99.60% AUC-ROC，优于 Silero-VAD、TEN-VAD 等。FireRedLID 支持100+语言与20+中文方言，于82语言的 FLEURS 数据集上达97.18%话语级准确率，超越 Whisper 与 SpeechBrain。FireRedPunc 基于 BERT 风格模型，对中英文实现标点预测，多领域平均F1达78.90%，高于 FunASR-Punc 的62.77%。项目代码与模型权重已开源至 https://github.com/FireRedTeam/FireRedASR2S。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。