feat: integrate wav2vec2 score into score fusion logic

fix: real ensemble inference, Youden threshold, DL unpickler

fix: add ffmpeg decoding fallback for audio loading in analyze_vocals

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

Refactor code structure for improved readability and maintainability

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

feat: add XAI inference service for explainable predictions with detailed feature contributions

feat: enhance feature extraction with additional spectral and temporal metrics

feat: extend AudioFeatures dataclass with additional spectral and temporal metrics

feat: add spectral rolloff and MFCC delta features to audio extraction

fix: improve error handling and logging in YouTubeAnalysisService

feat: enhance YouTubeDownloader with cookie handling and error normalization

feat: enhance YouTubeDownloader with cookie support and player client cycling

fix: add type annotation to _parse_response method for clarity

fix: refactor import statement and format model path for readability

fix: add docstring to Wav2Vec2DetectorService constructor for clarity

fix: add docstring to MetaClassifierService constructor for clarity

fix: add return type annotation to Wav2Vec2DetectorService constructor

fix: add return type annotation to MetaClassifierService constructor

feat: add wav2vec2 inference service for AURIS music detection

feat: implement meta-classifier service for AURIS score fusion

feat: add CLAP and FST indicators to score fusion results

feat: add parsing functions for CLAP and FST results in score fusion

feat: enhance fuse_scores function with CLAP and FST results integration

feat: add imports for CLAPResult and FSTResult in score_fusion.py

feat: add FST client for AI music detection using HuggingFace API

feat: implement CLAP-based AI music detection service

feat: add vocal analysis module for AI music detection

feat: implement score fusion engine for AI music detection

feat: add audio feature extraction module for AI music detection

fix: remove base_url from service_status response for cleaner output

fix: enhance error handling in YouTube analysis and implement API key validation with rate limiting

fix: enhance CORS origin handling and update validation for YouTube URLs

Initial commit: CrownCode Backend for Hugging Face Spaces