Constantinos Dimitriou's starred repositories
Wave-U-Net
Implementation of the Wave-U-Net for audio source separation
lightning-hydra-template
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
DiffSynth-Studio
Enjoy the magic of Diffusion models!
open-universe
Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.
DiscreteSpeechMetrics
Reference-aware automatic speech evaluation toolkit
CycleGAN-VC2
Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2
stable-audio-metrics
Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.
Wave-U-Net-Pytorch
Improved Wave-U-Net implemented in Pytorch
BS-RoFormer
Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
service-streamer
Boosting your Web Services of Deep Learning Applications.
coremltools
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
bss_speech_dataset
A dataset to test blind source separation algorithms
drum-pattern-datasets
This repository holds datasets of polyphonic drum patterns used in the creation of Electronic Dance Music.
dx7pytorch
A musical instrument audio dataset generated on-the-fly using FM synthesis.
Choral_Music_Separation
Chorale Music Separation Dataset and Model Framework