Multi-Modal Embeddings for Synthetic Transcript Filtering Collection This Repo contains all the models and plots for training a multimodal embeding models on two way loss (contrastive and binary crossentropy) • 4 items • Updated about 12 hours ago
yuriyvnv/whisper-large-v3-cv-capes-fs024-IEEE-pt Automatic Speech Recognition • 2B • Updated 2 days ago • 25
yuriyvnv/whisper-large-v3-cv-capes-fs024-IEEE-pt Automatic Speech Recognition • 2B • Updated 2 days ago • 25
yuriyvnv/whisper-large-v3-cv-capes-filtered-pt Automatic Speech Recognition • 2B • Updated 3 days ago • 36
yuriyvnv/whisper-large-v3-cv-capes-filtered-pt Automatic Speech Recognition • 2B • Updated 3 days ago • 36
yuriyvnv/whisper-large-v3-cv-capes-filtered-pt Automatic Speech Recognition • 2B • Updated 3 days ago • 36