Stars
A project that extracts Honkai: Star Rail text corpus
Extracting character conversations in Genshin Project
原神多语言文本搜索工具，可按关键字搜索所有文本、语音，可用于外语学习，剧情考据，模型训练等用途
Train transformer language models with reinforcement learning.
Align Anything: Training All-modality Model with Feedback
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
Official Repository for "SingFake: Singing Voice Deepfake Detection"
Your faithful, impartial partner for audio evaluation — know yourself and your rivals.真实评测，知己知彼。
Open-source framework for the research and development of foundation models.
An example starter repo for Python projects
Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction
A standardized toolkit of Kernel Audio Distance (KAD)—a distribution-free, unbiased, and computationally efficient metric for evaluating generative audio.
Unified automatic quality assessment for speech, music, and sound.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Code reporsitory for the INTERSPEECH 2024 paper - IndicMOS: Multilingual MOS Prediction for 7 Indian languages
A fundamental toolkit designed for music, song, and audio generation
A simple library for Fréchet Audio Distance (FAD) calculation
Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.
Awesome speech/audio LLMs, representation learning, and codec models
Speech Human Evaluation Estimation Toolkit (SHEET)