Matthew Baas's repositories
danbooru-pretrained
Pretrained pytorch models for the Danbooru2018 dataset
simple-speaker-embedding
A speaker embedding network in Pytorch that is very quick to set up and use for whatever purposes.
transfusion-asr
Transcribing Speech with Multinomial Diffusion, training code and models.
simple-asgan
Training code and trained checkpoints for ASGAN.
simple-autovc
A simple, performant re-implementation of AutoVC
simple-sashimi
A simple-to-use standalone Pytorch implementation of the SaShiMi speech synthesis model
DiffWave-unconditional
Pytorch Reimplementation of DiffWave unconditional generation: a high quality waveform synthesizer.
Experiment-K
Random experiments and testing 'out-there' ideas w.r.t machine learning and optimization
HierSpeechpp
Fork of HierSpeechpp with torchhub integration
mos-finetune-ssl
MOS predictor network with torchhub integration
simple-diffwave
DiffWave, adapted to be simple to use and train.
simple-speech-commands
A pretrained Pytorch classifier for the Google Speech Commands dataset that is very quick to set up and use.
audio_dbert
A general audio embedding model submitted for the HEAR 2021 challenge.
bitcoin-task-bounty
Spurring & cultivating Bitcoin development
CurveNet
Official implementation of "Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis", ICCV 2021, adapted for easier inference
fastai-telegram-callback
A fastai training callback that messages you the metrics on telegram after each epoch
nuwave2
NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates @ INTERSPEECH 2022
scudstorm
Scudstorm - Genetic algorithm for training a bot in Entelect's 2018 tower defense game
simple-pi-motion
Simple Raspberry Pi with camera module motion detection with Telegram notification
tf-logging-util
A simple script for setting the level of internal tensorflow logging to standard output