All projects
ast
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
Topics
Related projects
opencv90.9kOpen-source computer vision library providing fundamental image and video processing plus vision algorithms for developers building perception applications across domains.
Prompt-Engineering-Guide78.6kSystematic guide to prompt engineering compiling papers, tutorials, lectures, and techniques for readers learning, referencing, and practicing effective prompting methods.
ffmpeg64.4kGeneral-purpose multimedia library and toolset for encoding, decoding, muxing, filtering, transcoding, playback, and analysis of audio, video, and subtitles, supporting secondary development.
ultralytics61.9kMaintains the Ultralytics YOLO library for object detection, instance and semantic segmentation, image classification, pose estimation, and object tracking with pretrained models and training utilities.