# WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit

arXiv: https://arxiv.org/abs/2102.01547 · HTML: https://mlsanity.com/paper/2102.01547/

## Key facts

- Cited by 125 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 2 Feb 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Online and Linear-Time Attention by Enforcing Monotonic Alignments](https://mlsanity.com/paper/1704.00784/) (2017)
- [Monotonic Chunkwise Attention](https://mlsanity.com/paper/1712.05382/) (2017)
- [End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results](https://mlsanity.com/paper/1412.1602/) (2014)
- [MNN: A Universal and Efficient Inference Engine](https://mlsanity.com/paper/2002.12418/) (2020)
- [Deliberation Model Based Two-Pass End-to-End Speech Recognition](https://mlsanity.com/paper/2003.07962/) (2020)
- [Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition](https://mlsanity.com/paper/2012.05481/) (2020)
- [Transformer Based Deliberation for Two-Pass Speech Recognition](https://mlsanity.com/paper/2101.11577/) (2021)
- [Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture](https://mlsanity.com/paper/2001.08290/) (2020)
- [Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition](https://mlsanity.com/paper/2010.03192/) (2020)
- [Simplified Self-Attention for Transformer-based End-to-End Speech Recognition](https://mlsanity.com/paper/2005.10463/) (2020)
- [Enhancing Monotonic Multihead Attention for Streaming ASR](https://mlsanity.com/paper/2005.09394/) (2020)
- [Cascade RNN-Transducer: Syllable Based Streaming On-device Mandarin Speech Recognition with a Syllable-to-Character Converter](https://mlsanity.com/paper/2011.08469/) (2020)
- [Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling](https://mlsanity.com/paper/2010.06030/) (2020)
- [Exploring RNN-Transducer for Chinese Speech Recognition](https://mlsanity.com/paper/1811.05097/) (2018)

## Built on by (most cited first, 30 of 125)

- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM](https://mlsanity.com/paper/2411.00774/) (2024)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2305.11013/) (2023)
- [Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding](https://mlsanity.com/paper/2207.02971/) (2022)
- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction](https://mlsanity.com/paper/2604.27393/) (2026)
- [WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2203.15455/) (2022)
- [MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning](https://mlsanity.com/paper/2304.08981/) (2023)
- [U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition](https://mlsanity.com/paper/2106.05642/) (2021)
- [Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition](https://mlsanity.com/paper/2312.17279/) (2023)
- [Language-specific Characteristic Assistance for Code-switching Speech Recognition](https://mlsanity.com/paper/2206.14580/) (2022)
- [TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline](https://mlsanity.com/paper/2206.13135/) (2022)
- [Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model](https://mlsanity.com/paper/2209.01250/) (2022)
- [CR-CTC: Consistency regularization on CTC for improved speech recognition](https://mlsanity.com/paper/2410.05101/) (2024)
- [FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching](https://mlsanity.com/paper/2505.19476/) (2025)
- [Variable Attention Masking for Configurable Transformer Transducer Speech Recognition](https://mlsanity.com/paper/2211.01438/) (2022)
- [Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks](https://mlsanity.com/paper/2210.07499/) (2022)
- [Decoder-only Architecture for Streaming End-to-end Speech Recognition](https://mlsanity.com/paper/2406.16107/) (2024)
- [Easy Turn: Integrating Acoustic and Linguistic Modalities for Robust Turn-Taking in Full-Duplex Spoken Dialogue Systems](https://mlsanity.com/paper/2509.23938/) (2025)
- [Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation](https://mlsanity.com/paper/2205.08993/) (2022)
- [Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation](https://mlsanity.com/paper/2301.13003/) (2023)
- [CB-Conformer: Contextual biasing Conformer for biased word recognition](https://mlsanity.com/paper/2304.09607/) (2023)
- [CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition](https://mlsanity.com/paper/2502.18913/) (2025)
- [Rethinking Video Tokenization: A Conditioned Diffusion-based Approach](https://mlsanity.com/paper/2503.03708/) (2025)
- [Conversational Speech Recognition By Learning Conversation-level Characteristics](https://mlsanity.com/paper/2202.07855/) (2022)
- [Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR](https://mlsanity.com/paper/2309.13102/) (2023)
- [Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition](https://mlsanity.com/paper/2204.03855/) (2022)
- [4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders](https://mlsanity.com/paper/2212.10818/) (2022)

## Abstract (arXiv)

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. The main motivation of WeNet is to close the gap between the research and the production of E2E speechrecognition models. WeNet provides an efficient way to ship ASR applications in several real-world scenarios, which is the main difference and advantage to other open source E2E speech recognition toolkits. In our toolkit, a new two-pass method is implemented. Our method propose a dynamic chunk-based attention strategy of the the transformer layers to allow arbitrary right context length modifies in hybrid CTC/attention architecture. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final result. Our experiments on the AISHELL-1 dataset using WeNet show that, our model achieves 5.03% relative character error rate (CER) reduction in non-streaming ASR compared to a standard non-streaming transformer. After model quantification, our model perform reasonable RTF and latency.