OpenCodePapers

speech-recognition-on-aishell-1

Speech Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeWord Error Rate (WER)Params(M)ModelNameReleaseDate
FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration✓ Link0.551,100FireRedASR-AED2025-01-24
Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition0.68Seed-ASR2024-07-05
Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models✓ Link1.29Qwen-Audio2023-11-14
MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition✓ Link1.9MMSpeech With LM2022-11-29
FunASR: A Fundamental End-to-End Speech Recognition Toolkit✓ Link1.95220Paraformer-large2023-05-18
CR-CTC: Consistency regularization on CTC for improved speech recognition✓ Link4.0266.2Zipformer+CR-CTC (no external language model)2024-10-07
Lightweight Transducer Based on Frame-Level Criterion✓ Link4.0345.3Lightweight Transducer With LM2024-09-05
Improving Mandarin Speech Recogntion with Block-augmented Transformer✓ Link4.146SE-WSBO With LM2022-07-24
Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation✓ Link4.147CIF-HKD With LM2023-01-30
Lightweight Transducer Based on Frame-Level Criterion✓ Link4.3145.3Lightweight Transducer2024-09-05
Unimodal Aggregation for CTC-based Speech Recognition✓ Link4.744.7UMA2023-09-15
Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition✓ Link4.7247U22020-12-10
FunASR: A Fundamental End-to-End Speech Recognition Toolkit✓ Link4.9546.3Paraformer2023-05-18
BAT: Boundary aware transducer for memory-efficient and low-latency ASR✓ Link4.9790BAT2023-05-19
CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency✓ Link6.34CTC-CRF 4gram-LM2020-05-27
Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition6.638.5BRA-E2023-03-23
A Comparative Study on Transformer vs RNN in Speech Applications✓ Link6.7CTC/Att2019-09-13
End-to-end Speech Recognition with Adaptive Computation Steps18.7Att2018-08-30
Check out how to contribute new results.