Official implementation for the paper Fine-grained style control in transformer-based text-to-speech synthesis.

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

IMGUR5K handwriting set. It is a handwritten in-the-wild dataset, which contains challenging real world handwritten samples from different writers.The dataset is shared as a set of image urls with …

This repository contains the source code for the paper First Order Motion Model for Image Animation

AI Face Recognition/Person Detection NVR. Machine Learning On The Edge, turn your Camera into AI-powered with Jetson Nano and telegram to protect your privacy.

C++ library based on tensorrt integration

Implementation of popular deep learning networks with TensorRT network definition API

This repository deploys YOLOv4 as an optimized TensorRT engine to Triton Inference Server

This is a Multi object tracker. Mainly it was build for tracking car movement in a junction.

fire-smoke-detect-yolov4-yolov5 and fire-smoke-detection-dataset 火灾检测，烟雾检测

The official implementation of VAENAR-TTS, a VAE based non-autoregressive TTS model.

A Generative Flow for Text-to-Speech via Monotonic Alignment Search

End-to-End Speech Processing Toolkit

yolov5 deepsort 行人 车辆 跟踪 检测 计数

Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei and aishell3 datasets

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

Few-Shot Keyword Spotting

超快的中文普通话TTS

A Collection of Variational Autoencoders (VAE) in PyTorch.

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

multi-scale time domain speaker extraction

烟雾 火焰检测

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.