This is your work, valued

Western Cape, South Africa

Matthew Baas

Expert
@RF5

Electronic engineer and speech researcher. I'm interested in speech synthesis and generative speech models.

rf5.github.io

danbooru-pretrained. Pretrained pytorch models for the Danbooru2018 dataset

177

simple-speaker-embedding. A speaker embedding network in Pytorch that is very quick to set up and use for whatever purposes.

91

transfusion-asr. Transcribing Speech with Multinomial Diffusion, training code and models.

80

simple-asgan. Training code and trained checkpoints for ASGAN.

62

simple-autovc. A simple, performant re-implementation of AutoVC

22

lmao. Language Model Accessor Object - Neural autocomplete for Overleaf

13

simple-sashimi. A simple-to-use standalone Pytorch implementation of the SaShiMi speech synthesis model

4

simple-speech-commands. A pretrained Pytorch classifier for the Google Speech Commands dataset that is very quick to set up and use.

3

simple-pi-motion. Simple Raspberry Pi with camera module motion detection with Telegram notification

1

mos-finetune-ssl. MOS predictor network with torchhub integration

1

HierSpeechpp. Fork of HierSpeechpp with torchhub integration

1

Experiment-K. Random experiments, data, and testing 'out-there' ideas involving machine learning and stats

1

simple-diffwave. DiffWave, adapted to be simple to use and train.

1

DiffWave-unconditional. Pytorch Reimplementation of DiffWave unconditional generation: a high quality waveform synthesizer.

1