Speech Recognition
mravanelli/SincNet
SincNet is a neural architecture for efficiently processing raw audio samples.
PythonMITupdated Apr 28, 2021
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
$ git clone https://github.com/zzw922cn/Automatic_Speech_Recognition.gitSincNet is a neural architecture for efficiently processing raw audio samples.
▲ +373 ★ this week
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
▲ +12 ★ this week
A PyTorch-based Speech Toolkit
▲ +8 ★ this week
End-to-End Speech Processing Toolkit
▲ +8 ★ this week
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
Data from GitHub · snapshot Nov 16, 2026