Libraries & frameworks
kapre
keunwoochoi/kapre
Kapre provides Keras layers that compute STFT, inverse STFT, mel-spectrograms and related audio features on GPU in real time, making preprocessing part of the model.
Topics
Related projects
onnx21.7kAn open standard and Python package for AI model interoperability, defining a common graph format across frameworks.
audioFlux3.4kA Python and C library for audio and music analysis, providing time-frequency transforms, feature extraction, and music information retrieval algorithms for research and machine learning.
model-optimization1.6kA TensorFlow toolkit that optimizes Keras models for deployment with quantization, pruning, and clustering APIs.
wandb11.3kAn experiment tracking and observability platform for logging, visualizing, and managing machine learning training runs.
birdnet-go2.4kBirdNET-Go is a self-hosted soundscape analyzer that runs local AI models around the clock to identify birds, bats and other wildlife and surface detections in a web UI.
vocal-remover1.8kA deep-learning vocal separation tool that splits songs into vocals and instrumental tracks using pretrained PyTorch models, with optional scripts for training your own separator.