embeddings-extraction topic
List
embeddings-extraction repositories
Speaker-Diarization
15
Stars
2
Forks
Watchers
Identifying individual speakers in an audio stream based on the unique characteristics found in individual voices using Python
text-to-image-eval
19
Stars
0
Forks
Watchers
Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN...