practically universal music pre-processor
ISC License
CNN-based singing voice detection experiments
AudioLDM: Generate speech, sound effects, music and beyond, with text.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
语音感情识别
🎚️ Open Source Audio Matching and Mastering
Manipulate audio with a simple and easy high level interface
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
convolutional and recurrent estimators for music analysis
🔈 ⃕ 🖼
🎛 🔊 A Python library for audio.
基于PaddlePaddle实现端到端中文语音识别,从入门到实战,超简单的入门案例,超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
Versatile audio super resolution (any -> 48kHz) with AudioSR.
基于PaddlePaddle实现的音频分类,支持EcapaTdnn、PANNS、TDNN、Res2Net、ResNetSE等各种模型,还有多种预处理方法
本项目是基于PaddlePaddle的语音合成项目,使用的是VITS,VITS是一种语音合成方法,这种时端到端的模型使用起来非常简单,不需要文本对齐等太复杂的流程,直接一键训练和生成,大大降低了...
A library for audio and music analysis, feature extraction.