ishine's Projects
常用文本匹配模型tf版本,数据集为QA_corpus,持续更新中
A PyTorch-based knowledge distillation toolkit for natural language processing
Library for Textless Spoken Language Processing
Text normalization with Deep Learning
Code and model files for paper: I. Lourentzou et al., Adapting Sequence to Sequence models for Text Normalization in Social Media", ICSWM'19
TEXTOIR is a flexible toolkit for open intent detection and discovery. (ACL 2021)
it's a train acoustics model code lib
TensorFlow frozen forward model to plain C++ converter
Tensorflow implementation of Glow-TTS
An integration of Kaldi and Tensorflow to train a neural network based speaker verification system.
Tensorflow implementation of MLP-Mixer based TTS
LSTM for punctuation prediction implemented by TensorFlow.
A TensorFlow 2 Implementation of Conv-TasNet
Tensorflow 2.0 implementation of automatic punctuation with RNN + attention
Custom TensorFlow2 implementations of forward and backward computation of soft-DTW algorithm in batch mode.
Parallel Tacotron2's upsampling and auxiliary attention module.
Experiments with TF graphs
A Python library for Traversing the Tensorflow Computation Graphs and Converting them to other Formats.
Common classes and utils for Tensorflow
TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
GAN-based vocoder focusing on time and frequency features respectively
A Temporal-Spectral Generative Adversarial Network based End-to-end Packet Loss Concealment for Wideband Speech Transmission
Inspired by FastSpeech2