16 projects
julius
Nice DSP sweets: resampling, FFT Convolutions. All with PyTorch, differentiable and with CUDA support.
moshi
Moshi is moshi
treetable
Helper to pretty print an ascii table with a tree-like structure
moshi-mlx
Moshi is moshi, but running on macOS
seewav
Visualize waveform
rustymimi
moshi, a real-time voice AI
hibiki
Hibiki is Hibiki
audiocraft
Audio generation research library for PyTorch
demucs
Music source separation in the waveform domain.
flashy
Minimal solver for deep learning
dora-search
Easy grid searches for ML.
diffq
Differentiable quantization framework for PyTorch.
encodec
High fidelity neural audio codec
denoiser
Speech enhancement in the waveform domain. Supports offline and streaming evaluation. Implementation for https://arxiv.org/abs/2006.12847. For training, please directly clone the github repository.
brainmagick
Tools for MEG processing
prioheap
Priority queue with a sane API
