OpenCodePapers

speech-recognition-on-common-voice-english

Speech Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeTest WERModelNameReleaseDate
Step-Audio 2 Technical Report5.95Step-Audio 22025-08-27
Step-Audio 2 Technical Report✓ Link6.76Step-Audio 2 mini2025-08-27
NeMo: a toolkit for building AI applications using Neural Modules✓ Link6.99%canary-1b-flash2025-03-07
Step-Audio 2 Technical Report✓ Link7.83Kimi-Audio2025-04-25
NeMo: a toolkit for building AI applications using Neural Modules✓ Link7.97%canary-1b2024-02-08
NeMo: a toolkit for building AI applications using Neural Modules✓ Link8.0%ConformerCTC-L2019-09-14
Step-Audio 2 Technical Report8.33Qwen Omni2025-08-27
Scribosermo: Fast Speech-to-Text models for German and other Languages✓ Link9.06%ConformerCTC-L (5-gram)2021-10-15
Step-Audio 2 Technical Report9.20Doubao LLM ASR2025-08-27
Step-Audio 2 Technical Report9.30GPT-4o Transcribe2025-08-27
Scribosermo: Fast Speech-to-Text models for German and other Languages✓ Link14.38%ConformerCTC-L (5-gram, charbased)2021-10-15