Bring portraits to life!

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

Image augmentation for machine learning experiments.

Flexible Python configuration system. The last one you will ever need.

Matplotlib styles for scientific plotting

List of Computer Science courses with video lectures.

Web Application Framework in JavaScript and Objective-J

A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.

A python library for voice activity detection (VAD) for speech/non-speech segmentation.

The Voxseg implementation in PyTorch. Voxseg is a python library for voice activity detection (VAD) for speech/non-speech segmentation.

PyTorch implementations of Generative Adversarial Networks.

official implementation of VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning

Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.

Generating room impulse responses

Easy to use Beamformers for multi-channel speech separation/enhancement

This thesis applies an autoencoder deep neural network to the multichannel speech enhancement problem. It takes the problem from dataset generation to the model training

MultiSV: scripts for data preparation

Conformer-based Metric GAN for speech enhancement

Python bindings for llama.cpp

Fast and accurate spell correction library

Pure Python Spell Checking http://pyspellchecker.readthedocs.io/en/latest/

Real-Time De-noising and De-reverbing with Tiny Recurrent UNet

📷🔦💭 A 3D Scanner using Laser Structured Light, written in Python using OpenCV and NumPy.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Code for the paper "Language Models are Unsupervised Multitask Learners"

A python package to simulate typographical errors.

DNN-based SE in the frequency domain using Pytorch. You can test some state-of-the-art networks using T-F masking or spectral mapping method.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

SpotX patcher used for patching the desktop version of Spotify

⚡ Finetune Wa2vec 2.0 For Speech Recognition