None
EN
Unleashing gst-python-ml: Python-powered ML analytics for GStreamer pipelines
['Unleashing Gst-Python-Ml', 'Python-Powered Ml Analytics For Gstreamer Pipelines', 'Aaron Boxer']
Collabora Newsroom RSS Feed
We now take the next step by unleashing gst-python-ml: a pure Python framework that can easily build powerful ML-enabled GStreamer pipelines using standard Python packages. Object Detection with Yolo, FasterRCNN, MaskRCNN, or any TorchVision object detection model Segmentation with MaskRCNN or Yolo Tracking with Yolo Video Captioning with Phi3.5 Vision Translation with Marian Transcription with Whisper Speech to Text with Whisper Text to Speech with WhisperSpeech Text to Image with Stable Diffusion Bird's eye view of sports matches Batch inference Multiple incoming streams Large Language Models (LLMs) with any HuggingFace Hub LLM Serializing ML metadata to Kafka server for real-time post-processing Overlay to display ML metadata such as bounding boxes and tracks All elements are first…