muyangdu Goto Github PK

knowledgedistillation

PyTorch implementation of (Hinton) Knowledge Distillation and a base class for simple implementation of other distillation methods.

lightseq

LightSeq: A High Performance Library for Sequence Processing and Generation

linear-chain-crf

Implementation of a linear-chain CRF in PyTorch

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

lpcnet

Efficient neural speech synthesis

lpctorch

LPC Utility for Pytorch Library.

ml-glossary

Machine learning glossary

ml_equations_latex

Classical ML equations in Latex, helps paper and blog writing

muyangdu.github.io

nemo

Neural Modules: a toolkit for conversational AI

nlp_chinese_corpus

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

phrase-pinyin-data

词语拼音数据

polyphonedisambiguation

毕业设计-汉语多音字注音研究

pre-trained-models

预训练语言模型综述

promptpapers

Must-read papers on prompt-based tuning for pre-trained language models.

pytorch_backend

The Triton backend for the PyTorch TorchScript models.

pytorchltr

Learning to Rank in PyTorch

segan

Speech Enhancement Generative Adversarial Network in TensorFlow

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

speech-synthesis-paper

List of speech synthesis papers.

speechmetrics

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

tacotron

A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis

tacotron2

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

tensorrt-utils

⚡ Useful scripts and code references I use or encounter when working with TensorRT

uer-py

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

vall-e

An unofficial PyTorch implementation of the audio LM VALL-E

vall-e-x

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io

wavernn-heuristic-dynamic-blending

wenetspeechspeakercluster