{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/funasr-a-fundamental-end-to-end-speech","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","arxiv_id":"2305.11013","date":"2023-05-18","proceeding":null,"authors":["Zhifu Gao","Zerui Li","JiaMing Wang","Haoneng Luo","Xian Shi","Mengzhe Chen","Yabin Li","Lingyun Zuo","Zhihao Du","Zhangyu Xiao","Shiliang Zhang"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2305.11013v1","url_pdf":"https://arxiv.org/pdf/2305.11013v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"funasr-a-fundamental-end-to-end-speech","repo_url":"https://github.com/alibaba-damo-academy/FunASR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"activity-detection","task_name":"Activity Detection"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"memory-network","method_name":"Memory Network"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-aishell-1","task":"Speech Recognition","dataset":"AISHELL-1","model":"Paraformer-large","rank_in_archive_order":5,"of":18,"metrics":{"Params(M)":"220","Word Error Rate (WER)":"1.95"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-aishell-1","task":"Speech Recognition","dataset":"AISHELL-1","model":"Paraformer","rank_in_archive_order":13,"of":18,"metrics":{"Params(M)":"46.3","Word Error Rate (WER)":"4.95"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-aishell-2","task":"Speech Recognition","dataset":"AISHELL-2","model":"Paraformer-large","rank_in_archive_order":1,"of":2,"metrics":{"Word Error Rate (WER)":"2.85"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-aishell-2","task":"Speech Recognition","dataset":"AISHELL-2","model":"Paraformer","rank_in_archive_order":2,"of":2,"metrics":{"Word Error Rate (WER)":"5.73"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-wenetspeech","task":"Speech Recognition","dataset":"WenetSpeech","model":"Paraformer-large","rank_in_archive_order":1,"of":8,"metrics":{"Character Error Rate (CER)":"6.97"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.11013","atlas_url":"https://app.syntology.ai/?focus=2305.11013","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}