FireRedASR2-LLM-vllm

• FireRedASR2: Automatic Speech Recognition (ASR) supporting Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and singing lyrics recognition. 2.89% average CER on Mandarin (4 test sets), 11.55% on Chinese dialects (19 test sets), outperforming Doubao-ASR, Qwen3-ASR-1.7B, Fun-ASR, and Fun-ASR-Nano-2512. FireRedASR2-AED also supports word-level timestamps and confidence scores.
• FireRedVAD: Voice Activity Detection (VAD) supporting speech/singing/music in 100+ languages. 97.57% F1, outperforming Silero-VAD, TEN-VAD, and FunASR-VAD. Supports non-streaming/streaming VAD and Audio Event Detection.
• FireRedLID: Spoken Language Identification (LID) supporting 100+ languages and 20+ Chinese dialects/accents. 97.18% accuracy, outperforming Whisper and SpeechBrain-LID.
• FireRedPunc: Punctuation Prediction (Punc) for Chinese and English. 78.90% average F1, outperforming FunASR-Punc (62.77%).

2S: 2nd-generation FireRedASR, now expanded to an all-in-one ASR System

🔥 News

• [2026.02.25] 🔥 We release FireRedASR2-LLM model weights. 🤗 🤖
• [2026.02.13] 🚀 Support TensorRT-LLM inference acceleration for FireRedASR2-AED (contributed by NVIDIA). Benchmark on AISHELL-1 test set shows 12.7x speedup over PyTorch baseline (single H20).
• [2026.02.12] 🔥 We release FireRedASR2S (FireRedASR2-AED, FireRedVAD, FireRedLID, and FireRedPunc) with model weights and inference code. Download links below. Technical report and finetuning code coming soon.

Available Models and Languages

Method

FireRedASR2

FireRedASR2 builds upon FireRedASR with improved accuracy, designed to meet diverse requirements in superior performance and optimal efficiency across various applications. It comprises two variants:

• FireRedASR2-LLM: Designed to achieve state-of-the-art performance and to enable seamless end-to-end speech interaction. It adopts an Encoder-Adapter-LLM framework leveraging large language model (LLM) capabilities.
• FireRedASR2-AED: Designed to balance high performance and computational efficiency and to serve as an effective speech representation module in LLM-based speech models. It utilizes an Attention-based Encoder-Decoder (AED) architecture.

Other Modules

• FireRedVAD: DFSMN-based non-streaming/streaming Voice Activity Detection and Audio Event Detection.
• FireRedLID: FireRedASR2-based Spoken Language Identification. See FireRedLID README for language details.
• FireRedPunc: BERT-based Punctuation Prediction.

Evaluation

FireRedASR2

Metrics: Character Error Rate (CER%) for Chinese and Word Error Rate (WER%) for English. Lower is better.

We evaluate FireRedASR2 on 24 public test sets covering Mandarin, 20+ Chinese dialects/accents, and singing.

• Mandarin (4 test sets): 2.89% (LLM) / 3.05% (AED) average CER, outperforming Doubao-ASR (3.69%), Qwen3-ASR-1.7B (3.76%), Fun-ASR (4.16%) and Fun-ASR-Nano-2512 (4.55%).
• Dialects (19 test sets): 11.55% (LLM) / 11.67% (AED) average CER, outperforming Doubao-ASR (15.39%), Qwen3-ASR-1.7B (11.85%), Fun-ASR (12.76%) and Fun-ASR-Nano-2512 (15.07%).

Note: ws=WenetSpeech, md=MagicData, conv=Conversational, daily=Daily-use.