IMB-ASYNC benchmark suite is a collection of microbenchmark tools to estimate the MPI asynchronous progress performance (computation-communication overlap) in many useful scenarios. The scenarios i…

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

Imitating someone's handwriting by converting it to the temporal domain and back again

Source code for models described in the paper "ESResNe(X)t-fbsp: Learning Robust Time-Frequency Transformation of Audio" (https://arxiv.org/abs/2104.11587)

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

MelGAN vocoder (compatible with NVIDIA/tacotron2)

Code for the paper "Unsupervised Contrastive Learning of Sound Event Representations", ICASSP 2021.

This Repostory contains the pretrained DTLN-aec model for real-time acoustic echo cancellation.

Unsupervised acoustic word embeddings evaluated on Buckeye English and NCHLT Xitsonga data in Python 2.7.

National Novel Generation Month, 2020 edition.

A toolkit for symbolic music generation

Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch

C# client library for Twitch, YouTube Live, and other streaming services

AVSpeech downloader

Hierarchical fast and high-fidelity audio generation

Cross-platform .NET sample microservices and container based application that runs on Linux Windows and macOS. Powered by .NET 7, Docker Containers and Azure Kubernetes Services. Supports Visual St…

NVIDIA's Deep Imagination Team's PyTorch Library

Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.

FSL-Mate: A collection of resources for few-shot learning (FSL).

Synthesis of Drum Sounds With Perceptual Timbral Conditioning Using Generative Adversarial Networks

kapre: Keras Audio Preprocessors

GPT-3: Language Models are Few-Shot Learners

Resources on the topic of digital morphogenesis (creating form with code). Includes links to major articles, code repos, creative projects, books, software, and more.

LINQ provider for Oracle, PostgreSQL, MySQL, Ingres, SQLite, Firebird and ... SQL Server

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

Code for Unconditional Audio Generation with GAN and Cycle Regularization

Code for the paper "Jukebox: A Generative Model for Music"

[CVPR2020] Adversarial Latent Autoencoders