pan-yangxu Goto Github PK

gemmlowp

Low-precision matrix multiplication

gpt-sovits

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

grok-1

Grok open release

hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

how-to-optimize-gemm

incubator-mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

istftnet-pytorch

iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform

jackiexiao.github.io

My Blog

jieba

结巴中文分词

kazemotts

An open-source Kazakh Emotional Text-to-Speech Dataset

keras

Deep Learning for humans

larynx2

A fast, local neural text to speech system

leetcodetop

汇总各大互联网公司容易考察的高频leetcode题🔥

legacy_straight

A vocoder framework which had been widely used in research community since 1999.

libri-light

dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.

libriheavy

Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context

libtorch_tokenizer

BERT Tokenizer in C++

libtorchtutorials

This is a code repository for pytorch c++ (or libtorch) tutorial.

lightgrad

llama

Inference code for LLaMA models

llama-recipes

Examples and recipes for Llama 2 model

lpcnet

Efficient neural speech synthesis

mace

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

mahatts

map

Map for C, used rbtree to implement, sort by key

megatts2

Unoffical implementation of Megatts2

melgan

MelGAN vocoder (compatible with NVIDIA/tacotron2)

merlin

This is now the official location of the Merlin project.

mert

Official implementation of the paper "Acoustic Music Understanding Model with Large-Scale Self-supervised Training".

microprofile

microprofile is an embeddable profiler