Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Reduce audio row height (compact-audio CSS); sync dataset_loader

Results view: fix image size - force all 4 spec images to 700x280

Results: add Results (CLAP) and Results (Dasheng) views; dataset_loader supports dasheng results

Speed up: cache repo file list; Dasheng dropdown exclude fold*

Dasheng view: dropdown only shows batch_outputs_dasheng sample IDs (no fold*)

View options: Nearest Neighbor (CLAP) and Nearest Neighbor (Dasheng); dataset_loader supports batch_outputs_dasheng

Results view: show NN1/NN2/NN3 label for prompts

Results view: reorganize layout - Gaussian|Youtube row, Ours|NN baseline row

Increase NN spectrogram height to 480px

Increase NN spectrogram height to 320px

NN view: spec on top, BG/FG/Mix audios stacked vertically

NN view: one per row with prompt, top to bottom

NN view: NN1-NN10 from baseline (prompt order), no separate baseline block

Add view toggle: Nearest Neighbor (baseline + 10 NN) vs Results (3 baselines + Ours, top 3 prompts)

Layout: Baseline and Ours images side by side (height=320), audios below each

Restructure: per-prompt blocks with Baseline then Ours (1 image + 3 audios each)

Show retrieved prompt for each NN1/NN2/NN3

Add English instructions: ID sources (SONYC/UrbanSound8k), BG/FG/Mix labels

Remove Chinese from UI labels (Noise ID, image title)

Redesign UI: single noise selector, then Baseline/NN1/NN2/NN3 each with 1 image + 3 audios (BG/FG/Mix); add get_noise_demo_paths, no on-the-fly spectrogram

Fix Gradio 6.0 API and allow HF cache path for Spaces

Fix Gradio 6.0 API and allow HF cache path for Spaces

Add Gradio app: NN demo + comparison, dataset_loader, audio_utils, requirements

initial commit