SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper β’ 2602.12783 β’ Published Feb 13 β’ 168
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper β’ 2602.12783 β’ Published Feb 13 β’ 168
firdhokk/speech-emotion-recognition-with-openai-whisper-large-v3 Audio Classification β’ 0.6B β’ Updated Nov 1, 2025 β’ 13.4k β’ 107
stable-diffusion-v1-5/stable-diffusion-inpainting Text-to-Image β’ Updated Sep 6, 2024 β’ 192k β’ 101
Running on Zero 502 SDXL Inpainting π₯ 502 Inpaint images by replacing masked areas with AI-generated content