Papers › FunASR: A Fundamental End-to-End Speech Recognition Toolkit

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

18 May 2023arXiv:2305.11013archive 2025-07-28

Zhifu Gao, Zerui Li, JiaMing Wang, Haoneng Luo, Xian Shi, Mengzhe Chen, Yabin Li, Lingyun Zuo, Zhihao Du, Zhangyu Xiao, Shiliang Zhang

This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models trained on large-scale industrial corpora and the ability to deploy them in applications. The toolkit's flagship model, Paraformer, is a non-autoregressive end-to-end speech recognition model that has been trained on a manually annotated Mandarin speech recognition dataset that contains 60,000 hours of speech. To improve the performance of Paraformer, we have added timestamp prediction and hotword customization capabilities to the standard Paraformer backbone. In addition, to facilitate model deployment, we have open-sourced a voice activity detection model based on the Feedforward Sequential Memory Network (FSMN-VAD) and a text post-processing punctuation model based on the controllable time-delay Transformer (CT-Transformer), both of which were trained on industrial corpora. These functional modules provide a solid foundation for building high-precision long audio speech recognition services. Compared to other models trained on open datasets, Paraformer demonstrates superior performance.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

alibaba-damo-academy/FunASR officialmentioned in paperpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation (arXiv:2312.15185; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action DetectionActivity DetectionSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition AISHELL-1 Paraformer-large Params(M) 220 #5 of 18 Archive leaderboard report
Speech Recognition AISHELL-1 Paraformer-large Word Error Rate (WER) 1.95 #5 of 18 Archive leaderboard report
Speech Recognition AISHELL-1 Paraformer Params(M) 46.3 #13 of 18 Archive leaderboard report
Speech Recognition AISHELL-1 Paraformer Word Error Rate (WER) 4.95 #13 of 18 Archive leaderboard report
Speech Recognition AISHELL-2 Paraformer-large Word Error Rate (WER) 2.85 #1 of 2 Archive leaderboard report
Speech Recognition AISHELL-2 Paraformer Word Error Rate (WER) 5.73 #2 of 2 Archive leaderboard report
Speech Recognition WenetSpeech Paraformer-large Character Error Rate (CER) 6.97 #1 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMemory NetworkMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections