ishine's Projects
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
BERT for Coreference Resolution
比Sentence-BERT更有效的句向量方案
Official code for Cotatron @ INTERSPEECH 2020
Conversational Toolkit. An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
Deep Neural Network for Speaker Count Estimation
A bite of cpp api in PyTorch-1.0
how to design cpu gemm on x86 with avx256, that can beat openblas.
A dummy implementation of neural network.
爬取腾讯新闻首页所有新闻及其评论
python实现实时自动生成短视频
CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)
demo code of prosodic events prediction applying CRFs
A parametric Ambisonic decoder for headphones, based on the Cross-Pattern Coherence (CroPaC) spatial filter
CDCPP: Cross-Domain Chinese Punctuation Prediction
Tacotron 2 - PyTorch implementation with faster-than-realtime inference modified to enable cross lingual voice cloning.
Learning a common representation space from speech and text for cross-modal retrieval given textual queries and speech files.
PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
CRSS Implementation of speaker diarization system on a Kaldi-based platform
Crystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.
Pytorch implementation of CS-Tacotron, a code-switching speech synthesis end-to-end generative TTS model.
Companion repository for the paper "Continual Self-supervised Domain Adaptation for End-to-end Speaker Diarization"
PyTorch implementation of Continuous Speech Separation
Code for the ICASSP-2021 paper: Continuous Speech Separation with Conformer.
Code for the INTERSPEECH-2021 paper: Ultra Fast Speech Separation Model with Teacher Student Learning.