ZihanJin

Made-With-ML

Learn how to design, develop, deploy and iterate on production-grade ML applications.

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

awesome-scalability

The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

fish-speech

Brand new TTS solution

VoiceActivityProjection

Voice Activity Projection Models: Self-supervised learning of Turn-taking Events

TurnGPT

TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog

Books

Some special ebooks

manim

A community-maintained Python framework for creating mathematical animations.

MLE-LLaMA

Multi-language Enhanced LLaMA

BigVGAN

Official PyTorch implementation of BigVGAN (ICLR 2023)

AudioLDM

AudioLDM: Generate speech, sound effects, music and beyond, with text.

prosodic

Prosodic: a metrical-phonological parser, written in Python. For English and Finnish, with flexible language support.

hypher

Separates words into syllables.

Emotional-Speech-Data

This is the GitHub page for publicly available emotional speech data.

pytudes

Python programs, usually short, of considerable difficulty, to perfect particular skills.

cryptopunks-gan

Simple SN-GAN to generate CryptoPunks

visqol

Perceptual Quality Estimator for speech and audio

bert4pytorch

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

the-art-of-command-line

Master the command line, in one page

Python-for-Finance-Cookbook

Python for Finance Cookbook, published by Packt

audacitorch

PyTorch wrappers for using your model in audacity!

muzic

Muzic: Music Understanding and Generation with Artificial Intelligence

HUI-Audio-Corpus-German

This is the official repository for the HUI-Audio-Corpus-German. The corresponding paper is in the process of publication. With the repository it is possible to automatically recreate the dataset. It is also possible to add more speakers to the processing pipeline.

GFPGAN

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

russian_g2p

Accentor and transcriptor for Russian language

python-patterns

A collection of design patterns/idioms in Python

cuneiform

Machine translation and word embeddings of cuneiform corpuses

SMART-G2P

g2pK

g2pK: g2p module for Korean

mecab-python3

:snake: mecab-python. you can find original version here:http://taku910.github.io/mecab/