TensorFlow code and pre-trained models for BERT

A proxy tool to bypass GFW.

Deep neural networks for separating singing voice from music written in TensorFlow

Sequence to sequence learning using TensorFlow.

Seq2Seq Speech Recognition with Transformer on Mandarin Chinese

Source Separation Project For ML Jeju Camp 2017

TurnLite: TurnLite: Lightweight Interruption Detection(ICASSP 2026 Submission)

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

Trellis Networks for Sequence Modeling

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

Everything about Transfer Learning and Domain Adaptation--迁移学习