Speech Recognition
espnet/espnet🔥 active
End-to-End Speech Processing Toolkit
🌍 Machine Translation
PythonApache-2.0updated Sep 24, 2026
中文语音识别系列,读者可以借助它快速训练属于自己的中文语音识别模型,或直接使用预训练模型测试效果。
$ git clone https://github.com/binzhouchn/masr.gitEnd-to-End Speech Processing Toolkit
Machine Learning and Agentic AI Resources, Practice and Research
Tools for handling multimodal data in machine learning projects.
Pytorch实现的流式与非流式的自动语音识别框架,同时兼容在线和离线识别,目前支持Conformer、Squeezeformer、DeepSpeech2模型,支持多种数据增强方法。
ASR/NLP/TTS deep learning inference library for NVIDIA Jetson using PyTorch and TensorRT
Data from GitHub · snapshot Sep 24, 2026