本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

Official implementation of VQMIVC: One-shot (any-to-any) Voice Conversion @ Interspeech 2021 + Online playing demo!

vits chinese, tts chinese, tts mandarin 史上训练最简单，音质最好的语音合成系统，兼容性非常好的合成框架

超轻量级bert的pytorch版本，大量中文注释，容易修改结构，持续更新

简单的向量白化改善句向量质量

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.

STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech, Interspeech 2021

Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)

The code of "Dependency Parsing based Semantic Representation Learning with Graph Neural Network for Enhancing Expressiveness of Text-to-Speech"

Data Augmentation with a Generation Approach for Low-resource Tagging Tasks

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

Grapheme To Phoneme

A PyTorch implementation of Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

A fully tensorized recurrent neural network using tensor-train decomposition

Code for our EMNLP 2020 paper "Uncertainty-Aware Label Refinement for Sequence Labeling"

We start a company-name recognition task with a small scale and low quality training data, then using skills to enhanced model training speed and predicting performance with least artificial partic…

⏩ Generating speech in a single forward pass without any attention!

Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"

Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋

Updated list of public BitTorrent trackers

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

The Implementation of FastSpeech based on pytorch.

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility