A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

A Conversational Speech Generation Model

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

Low-precision matrix multiplication

System for AI Education Resource.

python script used to combine multiple channels of multiple .wav files into one multi-channel .wav file

CNN Textual RegressionModel for commodity price prediction

Tensorflow Implementation of paper Applying long short-term memory recurrent neural networks to intrusion detection with KDDCup99 Data

A simple GBDT in Python

常用机器学习的算法简洁实现

A high-level toolbox for using complex valued neural networks in PyTorch

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

Audio Classification with Noisy Dataset with multi stage semi-supervised learning

Kaggle Freesound Audio Tagging 2019 Competition Solution

This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.

SincNet is a neural architecture for efficiently processing raw audio samples.

Google Drive direct download of big files

Speech Enhancement using Bayesian WaveNet