Pawel Cyrta's Projects
Environment for automatic build of PocketSphinx Android app (speech recognition)
Polish BERT
Proste pobieranie podkastów z serwisu internetowego Polskiego Radia (polskieradio.pl)
some code experiments, checks, drafts - mostly shit
vamp features useful for segmentation, indexing, and retrieval of environmental sounds.
Breaks up bash scripts into steps.
SC tutorials
text normalization and cleaning - cli and python package [WIP]
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
SONYC project - UrbanSounds - dataset of sound recordings from New York, trying to recreate papers that classify the sound sources in the stream
mirror of VoxCeleb dataset - a large-scale speaker identification dataset
WaveNet vocoder