ishine's Projects
Open Neural Network Compiler
通用神经网络模型 onnx 在 RT-Thread 上的后端
A tool to modify onnx models in a visualization fashion, based on Netron and flask.
Open Neural Network Exchange model parser in C
Convert ONNX model graph to Keras model format.
ONNX Runtime: cross-platform, high performance scoring engine for ML models
Unofficial implementations of environmental sound synthesis system with Transformer
An open-source speech separation and enhancement library
Russian open STT dataset
Russian open TTS dataset
OpenAL Soft is a software implementation of the OpenAL 3D audio API.
A pytorch based end2end speech recognition system.
Open Source WFST-based Decoder Toolkit
Port of the OpenFST library to Windows
OpenFst 1.4.1 for Windows and Visual Studio 2013
An Open-Source Package for Neural Relation Extraction (NRE)
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
OpenSpeaker is a completely independent and open source speaker recognition project. It provides the entire process of speaker recognition including multi-platform deployment and model optimization.
A No-Recurrence Sequence-to-Sequence Model for Speech Recognition
Open Text to Speech Server
Open source UTAU successor
Sequence-to-sequence TTS based on Kyubyong's dc_tts
Stepwise optimizations of DGEMM on CPU, reaching performance faster than Intel MKL eventually, even under multithreading.
A neural network intent parser
Multi-platform embedded deep learning framework (『飞桨』多平台高性能嵌入式深度学习框架)
基于飞桨开发的虚拟主播
A Speech Toolkit based on PaddlePaddle.
[In-Progress] PyTorch implementation of "Pre-Alignment Guided Attention for Improving Training Efficiency and Model Stability in End-to-End Speech Synthesis"