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

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.

PDF Abstract

Results from the Paper

 Ranked #1 on Speech Recognition on WenetSpeech (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Speech Recognition AISHELL-1 Paraformer-large Word Error Rate (WER) 1.95 # 3
Params(M) 220 # 7
Speech Recognition AISHELL-1 Paraformer Word Error Rate (WER) 4.95 # 8
Params(M) 46.3 # 4
Speech Recognition AISHELL-2 Paraformer Word Error Rate (WER) 5.73 # 2
Speech Recognition AISHELL-2 Paraformer-large Word Error Rate (WER) 2.85 # 1
Speech Recognition WenetSpeech Paraformer-large Character Error Rate (CER) 6.97 # 1