symao's repositories
tensorrtx
Implementation of popular deep learning networks with TensorRT network definition API
Leaderboard
SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.
DL-Demos
Demos for deep learning
vocos
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
make-a-video-pytorch
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
vits-piper
A fast, local neural text to speech system
SpecVQGAN
Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)
SadTalker-Video-Lip-Sync
本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。
CharsiuG2P
Multilingual G2P in 100 languages
gruut
A tokenizer, text cleaner, and phonemizer for many human languages.
DL-Art-School
TorToiSe fine-tuning with DLAS
naturalspeech
A fully working pytorch implementation of NaturalSpeech (Tan et al., 2022)
Diffsound
The source code of our paper "Diffsound: discrete diffusion model for text-to-sound generation"
vits-cantonese
Cantonese Text to Speech with VITS implementation
TranSpeech
PyTorch Implementation of TranSpeech (ICLR'23): Textless NAR Speech-to-Speech Translation with Bilateral Perturbation
phonemizer
Simple text to phones converter for multiple languages
Awesome-Diffusion-Models
A collection of resources and papers on Diffusion Models
lyra
A Very Low-Bitrate Codec for Speech Compression
WMSeg-upgrade
This is the implementation of Improving Chinese Word Segmentation with Wordhood Memory Networks at ACL2020.
cmake-demo
《CMake入门实战》源码
open-speech-corpora
💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
chinese_speech_pretrain
chinese speech pretrained models
mmdetection-to-tensorrt
convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.
LibtorchTutorials
This is a code repository for pytorch c++ (or libtorch) tutorial.
Pytorch-Memory-Utils
pytorch memory track code
hifi-gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
TFGAN
TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
regnet
Official PyTorch implementation of the TIP paper "Generating Visually Aligned Sound from Videos" and the corresponding Visually Aligned Sound (VAS) dataset.