Speech Recognition
espnet/espnet🔥 active
▲ +10 ★ this week
End-to-End Speech Processing Toolkit
🌍 Machine Translation
PythonApache-2.0updated Nov 13, 2026
🏆 #6,383 overall#722 of 793 in Speech Recognition
roman-vygon /triplet_loss_kws
Learning Efficient Representations for Keyword Spotting with Triplet Loss
$ git clone https://github.com/roman-vygon/triplet_loss_kws.gitStars
115
115
This week
—
Forks
16
16
Language
Python
License
MIT
Created
Jan 26, 2021
5.8 years old
Last push
Sep 14, 2022
Categories
More in Speech Recognition
Speech Recognition
yanshengjia/ml-road
▲ +3 ★ this week
Machine Learning and Agentic AI Resources, Practice and Research
🧠 Natural Language Processing
PythonMITupdated Aug 1, 2026
Speech Recognition
lhotse-speech/lhotse🔥 active
▲ +3 ★ this week
Tools for handling multimodal data in machine learning projects.
PythonApache-2.0updated Nov 13, 2026
Speech Recognition
markovka17/dla🔥 active
▲ +1 ★ this week
Deep learning for audio processing
Jupyter NotebookMITupdated Nov 8, 2026
Speech Recognition
yeyupiaoling/MASR
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。
PythonApache-2.0updated Jul 6, 2026
Speech Recognition
binzhouchn/masr
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。
Pythonno licenseupdated Mar 23, 2021
Data from GitHub · snapshot Nov 13, 2026