Spaces:

Rthur2003
/

crowncode-backend

Build error

App Files Files Community

crowncode-backend / app

Commit History

Apr 28

09:58
feat: define families dictionary for candidate classifiers in _build_candidate_families function

Rthur2003

1d86705
09:57
feat: enhance candidate selection with class ratio and calibrated SVC for improved model performance

Rthur2003

57f19bf
09:56
feat: implement optimal threshold calculation for binary predictions in train function

Rthur2003

058eadc
09:55
feat: add CalibratedClassifierCV and roc_curve imports for enhanced model evaluation

Rthur2003

27cd744

Apr 24

13:12
feat: add TorchSklearnWrapper for PyTorch model compatibility with sklearn and enhance final model training process

Rthur2003

bb33480

Apr 16

09:38
Add Gradio dependency to requirements.txt with version constraints

Rthur2003

20fe6c3
09:04
feat: train all models on full data and save their paths

Rthur2003

94ed8e9
09:02
Refactor code structure for improved readability and maintainability

Rthur2003

c0f3b71
08:48
feat: update duration limit for audio analysis to 1 minute for improved detection

Rthur2003

d20e581
08:45
feat: implement mixed precision training and gradient accumulation in training loop

Rthur2003

076d979
08:44
feat: adjust confidence range in analysis result and optimize parallel processing for feature extraction, vocal analysis, and CLAP detection

Rthur2003

8e5e154
08:43
feat: enhance score fusion confidence range and adjust CLAP weight for improved accuracy

Rthur2003

e18d9f7
04:23
feat: adjust confidence calculation in score fusion to improve agreement handling

Rthur2003

ba5cc97
04:04
feat: update model parameters for Random Forest, Gradient Boosting, XGBoost, and LightGBM to enhance performance

Rthur2003

e68824c
04:02
feat: adjust Random Forest parameters for improved model performance

Rthur2003

905436c
04:02
feat: optimize Gradient Boosting and XGBoost parameters for improved model performance

Rthur2003

0d5b4e8
04:01
feat: refactor training history figure generation to use GradientBoostingClassifier and improve metric tracking

Rthur2003

1c2de42
03:56
feat: update model parameters and fix data leakage by removing duration_sec and sample_rate from features

Rthur2003

bb6655d
03:40
feat: add deep learning classifier comparison script for AURIS with multiple architectures

Rthur2003

b8d143b
03:38
feat: update excluded columns in feature statistics computation to prevent data leakage

Rthur2003

edc551d
03:24
feat: exclude additional metadata columns from feature loading to prevent data leakage

Rthur2003

4b87da0

Apr 15

19:59
feat: update output directory for generated figures to docs/academic/figures

Rthur2003

983f3ef
19:28
feat: add deep-learning figure generation script for enhanced model evaluation

Rthur2003

917199d
16:46
feat: enhance calibration figure with Brier score and update prediction functions

Rthur2003

255af12
16:44
feat: update ROC and Precision-Recall curve functions to include best model visualization

Rthur2003

ca749ec
16:42
feat: implement cross-validated predictions caching and update confusion matrix function

Rthur2003

0ea8f54
16:42
feat: add additional imports for model evaluation and cross-validation

Rthur2003

853f480
16:42
feat: add figure generation script for training results visualization

Rthur2003

94e94a1
16:35
feat: enhance analysis result with estimated bitrate and XAI verdict integration

Rthur2003

9e93437
16:34
feat: add XAI inference for explainable predictions in analysis results

Rthur2003

21d9516
16:34
feat: add XAI explanation models for enhanced interpretability in analysis results

Rthur2003

45def97
16:34
feat: integrate XAI service for enhanced explainability in analysis

Rthur2003

3f5c3a0
16:33
fix: rename variable for clarity in compute_stats function

Rthur2003

7e3e9a6
16:33
feat: add feature statistics computation from training CSV for enhanced analysis

Rthur2003

575dde4
16:32
feat: add XAI inference service for explainable predictions with detailed feature contributions

Rthur2003

ac52af9
08:15
feat: implement resume functionality in batch feature extraction to skip processed samples

Rthur2003

8f111ee

Apr 14

13:02
feat: enhance visualization pipeline with additional figures and manifest support

Rthur2003

b06ac73
13:01
feat: add dataset statistics and class balance visualizations to enhance analysis capabilities

Rthur2003

a04f1c8
12:58
feat: refactor worker function for batch feature extraction to support multiprocessing

Rthur2003

2a59987
12:57
feat: implement parallel processing for batch feature extraction to improve performance

Rthur2003

282a605

Apr 4

16:38
feat: extend analysis route to support multiple source types including TikTok, Instagram, SoundCloud, and Twitter

Rthur2003

f11faed

Mar 31

20:17
feat: add full training and evaluation pipeline for AURIS

Rthur2003

36a8a94
19:54
feat: enhance training pipeline with multi-model evaluation and detailed metrics

Rthur2003

5446f0d
19:52
feat: enhance feature extraction with additional spectral and temporal metrics

Rthur2003

7f1ed48
19:51
feat: extend AudioFeatures dataclass with additional spectral and temporal metrics

Rthur2003

7b2d19a
19:51
feat: add spectral rolloff and MFCC delta features to audio extraction

Rthur2003

017841c
09:12
fix: improve error handling and logging in YouTubeAnalysisService

Rthur2003

c5dd8f6
09:11
feat: enhance YouTubeDownloader with cookie handling and error normalization

Rthur2003

8bf6e42
08:54
feat: enhance YouTubeDownloader with cookie support and player client cycling

Rthur2003

13ab660
08:48
fix: gitignore models/data and add logging to feature extraction⁠

Rthur2003 +1: Claude Opus 4.6

d33093c

Commit History

Apr 28

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

Apr 24

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

Apr 16

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 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

feat: update model parameters for Random Forest, Gradient Boosting, XGBoost, and LightGBM to enhance performance

feat: adjust Random Forest parameters for improved model performance

feat: optimize Gradient Boosting and XGBoost parameters for improved model performance

feat: refactor training history figure generation to use GradientBoostingClassifier and improve metric tracking

feat: update model parameters and fix data leakage by removing duration_sec and sample_rate from features

feat: add deep learning classifier comparison script for AURIS with multiple architectures

feat: update excluded columns in feature statistics computation to prevent data leakage

feat: exclude additional metadata columns from feature loading to prevent data leakage

Apr 15

feat: update output directory for generated figures to docs/academic/figures

feat: add deep-learning figure generation script for enhanced model evaluation

feat: enhance calibration figure with Brier score and update prediction functions

feat: update ROC and Precision-Recall curve functions to include best model visualization

feat: implement cross-validated predictions caching and update confusion matrix function

feat: add additional imports for model evaluation and cross-validation

feat: add figure generation script for training results visualization

feat: enhance analysis result with estimated bitrate and XAI verdict integration

feat: add XAI inference for explainable predictions in analysis results

feat: add XAI explanation models for enhanced interpretability in analysis results

feat: integrate XAI service for enhanced explainability in analysis

fix: rename variable for clarity in compute_stats function

feat: add feature statistics computation from training CSV for enhanced analysis

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

feat: implement resume functionality in batch feature extraction to skip processed samples

Apr 14

feat: enhance visualization pipeline with additional figures and manifest support

feat: add dataset statistics and class balance visualizations to enhance analysis capabilities

feat: refactor worker function for batch feature extraction to support multiprocessing

feat: implement parallel processing for batch feature extraction to improve performance

Apr 4

feat: extend analysis route to support multiple source types including TikTok, Instagram, SoundCloud, and Twitter

Mar 31

feat: add full training and evaluation pipeline for AURIS

feat: enhance training pipeline with multi-model evaluation and detailed metrics

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: gitignore models/data and add logging to feature extraction⁠