# sirichandana-jpg/indian-folk-music-classification architecture

> Architecture diagram of the GitHub repository sirichandana-jpg/indian-folk-music-classification, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sirichandana-jpg/indian-folk-music-classification
- Repository: https://github.com/sirichandana-jpg/indian-folk-music-classification

## Overview

This is an Indian folk music genre-classification system: users provide audio and receive a predicted genre with confidence, while the project also supports feature analysis, model training, and evaluation. The graph shows the Streamlit inference route and the documented training/model capabilities. Preparation and evaluation details are limited to what the README and source index establish; unsampled relationships are omitted.

Main entry points: [`models/model_factory.py`](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/model_factory.py) (Model factory), [`streamlit_app/app.py`](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/streamlit_app/app.py) (Streamlit interface), [`training/trainer.py`](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/training/trainer.py) (Training engine), [`streamlit_app/app_utils.py`](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/streamlit_app/app_utils.py) (Inference helpers)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_inference["Audio inference"]
  node_app["Streamlit interface<br/>[app.py]"]
  node_inference_helpers["Inference helpers<br/>[app_utils.py]"]
end

subgraph group_signals["Signal processing"]
  node_preprocessor["Audio preprocessing"]
  node_extractor["Feature extraction"]
  node_visualizer["Audio visualization"]
end

subgraph group_learning["Model learning"]
  node_augmentation["Audio augmentation<br/>[augmentor.py]"]
  node_trainer["Training engine<br/>[trainer.py]"]
  node_metrics["Training metrics<br/>[metrics.py]"]
  node_model_factory["Model factory<br/>[model_factory.py]"]
  node_base_model["Model base<br/>[base_model.py]"]
  node_cnn["2D CNN<br/>[cnn_2d.py]"]
  node_cnn_bilstm["CNN BiLSTM<br/>[cnn_bilstm.py]"]
  node_crnn["CRNN<br/>[crnn.py]"]
  node_training_entry["Training entry<br/>[train.py]"]
  node_evaluation["Model evaluation<br/>[evaluate_crnn.py]"]
end

subgraph group_support["Shared support"]
  node_config["Configuration loader<br/>[config_parser.py]"]
  node_logger["Logging<br/>[logger.py]"]
end

node_user(("Audio user"))

node_user -->|"provides audio"| node_app
node_app -->|"preprocesses audio"| node_preprocessor
node_app -->|"requests inference"| node_inference_helpers
node_app -->|"extracts display features"| node_extractor
node_app -->|"renders plots"| node_visualizer
node_inference_helpers -->|"extracts model features"| node_extractor
node_inference_helpers -->|"builds model"| node_model_factory
node_inference_helpers -->|"returns genre scores"| node_user
node_training_entry -->|"loads settings"| node_config
node_training_entry -->|"builds model"| node_model_factory
node_training_entry -->|"starts training"| node_trainer
node_trainer -->|"augments samples"| node_augmentation
node_trainer -->|"extracts features"| node_extractor
node_trainer -->|"computes metrics"| node_metrics
node_model_factory -->|"constructs"| node_cnn
node_model_factory -->|"constructs"| node_cnn_bilstm
node_model_factory -->|"constructs"| node_crnn
node_cnn -->|"inherits from"| node_base_model
node_cnn_bilstm -->|"inherits from"| node_base_model
node_crnn -->|"inherits from"| node_base_model
node_evaluation -->|"builds model"| node_model_factory
node_evaluation -->|"evaluates model"| node_trainer

click node_app "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/streamlit_app/app.py"
click node_inference_helpers "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/streamlit_app/app_utils.py"
click node_preprocessor "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/preprocessing/audio_preprocessor.py"
click node_extractor "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/feature_extraction/feature_extractor.py"
click node_visualizer "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/visualization/audio_visualizer.py"
click node_augmentation "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/augmentation/augmentor.py"
click node_trainer "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/training/trainer.py"
click node_metrics "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/training/metrics.py"
click node_model_factory "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/model_factory.py"
click node_base_model "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/base_model.py"
click node_cnn "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/cnn_2d.py"
click node_cnn_bilstm "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/cnn_bilstm.py"
click node_crnn "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/crnn.py"
click node_training_entry "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/train.py"
click node_evaluation "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/evaluate_crnn.py"
click node_config "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/utils/config_parser.py"
click node_logger "https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/utils/logger.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_app,node_inference_helpers,node_user toneBlue
class node_preprocessor,node_extractor,node_visualizer toneAmber
class node_augmentation,node_trainer,node_metrics,node_model_factory,node_base_model,node_cnn,node_cnn_bilstm,node_crnn,node_training_entry,node_evaluation toneMint
class node_config,node_logger toneRose
```

## Components

### Audio inference

- [Streamlit interface](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/streamlit_app/app.py): `streamlit_app/app.py`
- [Inference helpers](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/streamlit_app/app_utils.py): `streamlit_app/app_utils.py`

### Signal processing

- [Audio preprocessing](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/preprocessing/audio_preprocessor.py): `preprocessing/audio_preprocessor.py`
- [Feature extraction](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/feature_extraction/feature_extractor.py): `feature_extraction/feature_extractor.py`
- [Audio visualization](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/visualization/audio_visualizer.py): `visualization/audio_visualizer.py`

### Model learning

- [Audio augmentation](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/augmentation/augmentor.py): `augmentation/augmentor.py`
- [Training engine](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/training/trainer.py): `training/trainer.py`
- [Training metrics](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/training/metrics.py): `training/metrics.py`
- [Model factory](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/model_factory.py): `models/model_factory.py`
- [Model base](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/base_model.py): `models/base_model.py`
- [2D CNN](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/cnn_2d.py): `models/cnn_2d.py`
- [CNN BiLSTM](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/cnn_bilstm.py): `models/cnn_bilstm.py`
- [CRNN](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/models/crnn.py): `models/crnn.py`
- [Training entry](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/train.py): `train.py`
- [Model evaluation](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/evaluate_crnn.py): `evaluate_crnn.py`

### Shared support

- [Configuration loader](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/utils/config_parser.py): `utils/config_parser.py`
- [Logging](https://github.com/sirichandana-jpg/indian-folk-music-classification/blob/master/utils/logger.py): `utils/logger.py`

### Other components

- **Audio user**

## Connections

- Audio user → Streamlit interface: provides audio (evidence: `streamlit_app/app.py`)
- Streamlit interface → Audio preprocessing: preprocesses audio (evidence: `streamlit_app/app.py`)
- Streamlit interface → Inference helpers: requests inference (evidence: `streamlit_app/app.py`)
- Streamlit interface → Feature extraction: extracts display features (evidence: `streamlit_app/app.py`)
- Streamlit interface → Audio visualization: renders plots (evidence: `streamlit_app/app.py`)
- Inference helpers → Feature extraction: extracts model features (evidence: `streamlit_app/app_utils.py`)
- Inference helpers → Model factory: builds model (evidence: `streamlit_app/app_utils.py`)
- Inference helpers → Audio user: returns genre scores (evidence: `streamlit_app/app_utils.py`)
- Training entry → Configuration loader: loads settings (evidence: `train.py`)
- Training entry → Model factory: builds model (evidence: `train.py`)
- Training entry → Training engine: starts training (evidence: `train.py`)
- Training engine → Audio augmentation: augments samples (evidence: `training/trainer.py`)
- Training engine → Feature extraction: extracts features (evidence: `training/trainer.py`)
- Training engine → Training metrics: computes metrics (evidence: `training/trainer.py`)
- Model factory → 2D CNN: constructs (evidence: `models/model_factory.py`)
- Model factory → CNN BiLSTM: constructs (evidence: `models/model_factory.py`)
- Model factory → CRNN: constructs (evidence: `models/model_factory.py`)
- 2D CNN → Model base: inherits from (evidence: `models/cnn_2d.py`)
- CNN BiLSTM → Model base: inherits from (evidence: `models/cnn_bilstm.py`)
- CRNN → Model base: inherits from (evidence: `models/crnn.py`)
- Model evaluation → Model factory: builds model (evidence: `evaluate_crnn.py`)
- Model evaluation → Training engine: evaluates model (evidence: `evaluate_crnn.py`)
