Qwen3 Voice Embedding Collection Standalone ECAPA-TDNN x-vector speaker encoders extracted from Qwen3-TTS. 1024-dim (0.6B) and 2048-dim (1.7B). β’ 4 items β’ Updated Feb 27 β’ 29
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper β’ 2502.14786 β’ Published Feb 20, 2025 β’ 164
AIMv2 Collection A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. β’ 16 items β’ Updated Mar 2 β’ 83
view article Article Training and Finetuning Embedding Models with Sentence Transformers May 28, 2024 β’ 273