# marlinspike/whisper_transcribe_video architecture

> Architecture diagram of the GitHub repository marlinspike/whisper_transcribe_video, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2024-12-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/marlinspike/whisper_transcribe_video
- Repository: https://github.com/marlinspike/whisper_transcribe_video

## Overview

##### Main Components

a) External Services:
- YouTube Data Source
- Azure OpenAI Service (Whisper Model)

b) Application Components:
- Main Application Controller (app.py)
- Audio Processing Engine (audio_engine.py)
- File Download Manager (file_downloader.py)
- Batch Processing System (batch_processor.py)

c) Storage Components:
- Working Directory (temporary storage)
- Output Directory (transcription storage)
- Configuration (.env)

**┌─ Input Sources ─┐    ┌─ Core Processing ─┐    ┌─ External Services ─┐**
- YouTube URLs  │    │ - File Downloader │    │ - Azure OpenAI      │
- Local Files   │──►│ - Audio Engine    │◄──►│   (Whisper)         │
- Batch CSV     │    │ - Batch Processor │    └───────────────────┘
- ┘    └────────────────────┘

- ┌─ Storage ─┐
- Working Dir │
- ┴─────────────────►│ - Output Dir  │
- ┘

##### Process Flow Representation

a) Input Processing Flow:
- YouTube URL/Local File/CSV → File Downloader
- File Downloader → Working Directory

b) Processing Flow:
- Working Directory → Audio Engine
- Audio Engine → Azure OpenAI Whisper
- Azure OpenAI Whisper → Audio Engine
- Audio Engine → Output Directory

c) Batch Processing Flow:
- CSV File → Batch Processor
- Batch Processor → File Downloader
- Batch Processor → Audio Engine

##### Important Details

a) File Processing Stages:
- Download Stage
- Audio Splitting Stage (with configurable splits)
- Transcription Stage
- Cleanup Stage

b) Configuration Elements:
- Environment Variables
- Split Configuration
- API Endpoints

##### Technical Specifications to Note

- FFmpeg dependency for audio processing
- Python 3.11+ requirement
- Azure OpenAI Whisper model location (North Central region)
- File format support (Audio/Video)

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% Styles and Classes
    classDef external fill:#b3d1ff,stroke:#4d88ff
    classDef core fill:#b3ffb3,stroke:#4d994d
    classDef storage fill:#fff2b3,stroke:#e6b800
    classDef input fill:#ffd9b3,stroke:#ff9933
    classDef config fill:#ffb3d1,stroke:#ff4d94

    %% Legend
    subgraph Legend
        L1[External Services]:::external
        L2[Core Components]:::core
        L3[Storage Components]:::storage
        L4[Input Sources]:::input
        L5[Configuration]:::config
    end

    %% Input Sources
    subgraph InputSources
        YT[YouTube URLs]:::input
        LF[Local Files]:::input
        CSV["youtube_videos.csv"]:::input
    end

    %% External Services
    subgraph ExternalServices
        YouTube[YouTube Service]:::external
        AzureAI[Azure OpenAI Whisper]:::external
    end

    %% Core Processing
    subgraph CoreProcessing
        FD["File Download Manager"]:::core
        AE["Audio Processing Engine"]:::core
        BP["Batch Processor"]:::core
        APP["Main Application Controller"]:::core
    end

    %% Storage
    subgraph Storage
        WD[Working Directory]:::storage
        OD["Output Directory<br>transcription.txt"]:::storage
    end

    %% Configuration
    Config[".env Configuration"]:::config

    %% Relationships
    YT --> FD
    LF --> FD
    CSV --> BP
    BP --> FD
    FD --> YouTube
    FD --> WD
    WD --> AE
    AE --> AzureAI
    AzureAI --> AE
    AE --> OD
    Config --> APP
    APP --> BP
    APP --> FD
    APP --> AE

    %% Click Events
    click APP "https://github.com/marlinspike/whisper_transcribe_video/blob/main/app.py"
    click AE "https://github.com/marlinspike/whisper_transcribe_video/blob/main/audio_engine.py"
    click FD "https://github.com/marlinspike/whisper_transcribe_video/blob/main/file_downloader.py"
    click BP "https://github.com/marlinspike/whisper_transcribe_video/blob/main/batch_processor.py"
    click Config "https://github.com/marlinspike/whisper_transcribe_video/blob/main/.env.example"
    click CSV "https://github.com/marlinspike/whisper_transcribe_video/blob/main/youtube_videos.csv"
    click OD "https://github.com/marlinspike/whisper_transcribe_video/blob/main/transcription.txt"
```
