There are 2 repositories under paraformer topic.
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
商用级开源语音自动识别程序库,开箱即用,全平台支持,中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide a set of easier APIs to call ASR models.
Computes the MWER (minimum WER) Loss with beam search and negative sampling strategy.
语音转文本的各类python封装实现(paraformer、whisper_online、whisper_offline、funasr),用于服务kuon仓库