Extract hardcoded subtitles from videos using machine learning

AwesomeTTS Anki Addon

A micro implementation of React.js and ReactDOM named '@cw1997/ez-react' and '@cw1997/ez-react-dom' You can use these libraries as a mini edition of official React.js and ReactDOM.

changwei's blog

好耶 是女装

基于 g2pW 提升 pypinyin 的准确性

更纯粹、更高压缩率的Tokenizer

沉浸式双语网页翻译扩展 , 支持输入框翻译， 鼠标悬停翻译， PDF, Epub, 字幕文件, TXT 文件翻译 - Immersive Dual Web Page Translation Extension

Mouseover Translate Any Language At Once - Chrome Extension: PDF Translator, EBOOK, EPUB, OCR, TTS, NETFLIX, YOUTUBE DUAL SUBTITLES, GOOGLE DOCS, AI, VIEWER, GMAIL, WRITING, IMAGE, DUAL SUBS, MANGA…

first base model for full-duplex conversational audio

Windows 10 & 11 Samsung Galaxy Book Spoofer + Patched Samsung System Support Service -- Tool/guide for making *some* Samsung apps work on any Windows 10 and 11 PCs (Bypass the "This app only works …

Fast inference engine for Transformer models

[Kaggle-2nd] Lightweight yet Effective Chinese LLM.

Pipelined MIPS processor in Verilog

好耶 是女装 | 备份·接受PR

justfont collaborates with calligrapher Daphne to release Elffont (精靈文), a unique typeface blending Bopomofo phonetic symbols with a mystical "Elvish" style.

Website for the Subword Modeling course

Animation engine for explanatory math videos

O1 Replication Journey

A Survey on Neural Audio Codec

Official implementation of MelHuBERT

A lightweight keyboard for Android

This repository focuses on leveraging OpenAI's Whisper model for speech recognition in Chinese (Mandarin) and Taiwanese Hokkien languages. It includes tools and scripts for data preprocessing, mode…

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.