Libraries & frameworks
audio
pytorch/audio
TorchAudio, PyTorch's official library for loading audio datasets and applying transforms such as spectrograms, MFCC, and resampling in machine learning pipelines.
Topics
Related projects
voxcpm41.3kAn open-source 2B tokenizer-free multilingual TTS model for voice design, controllable cloning, and studio-quality synthesis.
kornia12.3kA differentiable computer vision library built on PyTorch for image processing, geometric vision, and augmentation pipelines.
cleanrl10.7kHigh-quality single-file deep RL library covering PPO, DQN and SAC, focused on readability and reproducible experiment management.
audiomentations2.3kAudiomentations is a Python library for audio data augmentation, offering composable transforms that help audio machine-learning models generalize beyond the lab.
CompressAI1.7kA PyTorch library and evaluation platform for learned image and video compression with pretrained models and training tools.
DawDreamer1.3kDawDreamer is a Python framework for constructing and rendering digital audio workflows, hosting VST instruments and effects, automating parameters and experimenting with FAUST, JAX and machine learning.