SOTA discrete codec models with forty tokens one second for audio language modeling

Code for CTX-vec2wav in UniCATS

Kandinsky 2 — multilingual text2image latent diffusion model

TigerBot: A multi-language multi-task LLM

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Scripts for training a phrase break prediction system

Voice conversion with just k-nearest neighbors

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

List of 4000 Chinese characters sorted by historical usage frequency, with Cantonese yale romanization and definition

chinese NLP corpus of chinese science fiction,chinese science fiction corpus : About 4675 Chinese science fiction novels 大约有4675本科幻小说，中文科幻小说自然语言处理语料库，中文科幻小说文本语料库，中文科幻小说文本数据库，科幻小说语料

chinese NLP corpus of chinese science fiction, chinese science fiction corpus: Archive of the Ark Plan of Ula Science Fiction Website 乌拉科幻小说网方舟计划存档，中文科幻小说自然语言处理语料库，中文科幻小说文本语料库，中文科幻小说文本数据库，科幻小说语料

Adaptive Vocoder for Custom Voice

Chinese Mandarin Grapheme-to-Phoneme Converter. 中文轉注音或拼音 (INTERSPEECH 2022)

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

VoiceSmith makes training text to speech models easy.

Noise supression using deep filtering

JKTime

Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

Python - 100天从新手到大师

Anno is a thin user interface on Markdown files for easy and local text editing, organization, and portability.

GSoC'2021 | TensorFlow implementation of Wav2Vec2

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

📼 A cheatsheet for common video processing operations in FFmpeg

离线字帖生成器