fix: extend xlim in plot_ml_vs_dl to prevent clipping of value labels

fix: add lightgbm and xgboost to requirements.txt

feat: integrate wav2vec2 score into score fusion logic

fix: add wav2vec2 result handling and logging in analyze file processing

feat: add Wav2Vec2 detector service to analysis route

fix: correct AURIS model repository ID in Dockerfile, startup script, and upload script

fix: adjust confidence calculation and streamline model download logic

fix: real ensemble inference, Youden threshold, DL unpickler

docs: update README with model hub deployment steps and new env vars

feat: add startup script for model downloads and upload script for Hugging Face Hub

fix: update calibration and precision-recall plotting functions to load data from files

fix: update confusion matrix and score distribution functions to load pre-computed CV predictions

feat: add script to generate publication-ready figures for AURIS paper

fix: add ffmpeg decoding fallback for audio loading in analyze_vocals

fix: add ffmpeg decoding fallback for unsupported audio formats in feature extraction

fix: comment out spotdl due to conflicts with gradio

fix: update fastapi and uvicorn versions in requirements.txt

fix: update evaluation to use optimal threshold and adjust BCEWithLogitsLoss for class imbalance

fix: adjust BCEWithLogitsLoss to handle class imbalance with pos_weight

fix: add missing roc_curve metric import for evaluation

feat: add wav2vec2 model display in build_models_md function

feat: enhance model table HTML with wav2vec2 badge and formatted metrics

feat: add audio path parameter to _build_model_table_html and include wav2vec2 predictions

feat: implement wav2vec2 model loading and inference functions for audio processing

feat: add wav2vec2_model to artifacts loading for enhanced model integration

feat: add wav2vec2_model attribute to DemoArtifacts for model integration

feat: add Wav2Vec2Config and Wav2Vec2MusicClassifier imports for audio classification

feat: define families dictionary for candidate classifiers in _build_candidate_families function

feat: enhance candidate selection with class ratio and calibrated SVC for improved model performance

feat: implement optimal threshold calculation for binary predictions in train function

feat: add CalibratedClassifierCV and roc_curve imports for enhanced model evaluation

feat: add temporary file patterns to .gitignore for dashboard images

feat: implement custom unpickler for TorchSklearnWrapper to support model deserialization

feat: add TorchSklearnWrapper import for model deserialization support

feat: enhance model compatibility and input handling for deep learning wrappers

feat: add TorchSklearnWrapper for PyTorch model compatibility with sklearn and enhance final model training process

feat: enhance Windows compatibility for asyncio with warning suppression

feat: add Gradio import handling and Windows compatibility for asyncio

Add Gradio dependency to requirements.txt with version constraints

feat: train all models on full data and save their paths

Refactor code structure for improved readability and maintainability

feat: update gauge and bars temperature images for improved visualization

feat: update local demo for AURIS AI music detection with enhanced dashboard and model comparison

Add gauge temperature image generated by Matplotlib

feat: add local demo for AURIS AI music detection with Gradio interface

feat: update duration limit for audio analysis to 1 minute for improved detection

feat: implement mixed precision training and gradient accumulation in training loop

feat: adjust confidence range in analysis result and optimize parallel processing for feature extraction, vocal analysis, and CLAP detection

feat: enhance score fusion confidence range and adjust CLAP weight for improved accuracy

feat: adjust confidence calculation in score fusion to improve agreement handling