# prince1314-patel/multi-speaker-diarization architecture

> Architecture diagram of the GitHub repository prince1314-patel/multi-speaker-diarization, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-08-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/prince1314-patel/multi-speaker-diarization
- Repository: https://github.com/prince1314-patel/multi-speaker-diarization

## Overview

##### Project type and purpose
- This is a Python‐based, modular multi-speaker meeting transcription system.
- It ingests audio in various formats, performs speaker diarization and ASR transcription using NVIDIA NeMo, WhisperX, and pyannote-audio, then exports results. An optional Streamlit UI provides upload and visualization.

##### File structure
- Top-level:
- .gitignore
- README.md
- Implicit subcomponents (in code):
- Ingestion module (handles .wav, .mp3 via librosa, pydub, ffmpeg)
- Diarization engines (pyannote-audio, NeMo, WhisperX)
- Transcription engine (ASR via nemo_toolkit[asr])
- Configuration (omegaconf, python-dotenv)
- Output exporters (.txt, .csv, .json, .srt/.vtt)
- Optional Streamlit frontend for UI
- Tests (pytest)

##### README for additional insights
- Describes modular, secure, scalable design.
- Two branch strategies: pure pyannote-audio vs hybrid whisperX+pyannote.
- Key dependencies define technology choices.

##### Elements
- Clear labels: e.g., “Audio Ingestion”, “Speaker Diarization”, “ASR Transcription”
- Blue rectangles for core processing modules
- Orange parallelograms for input/output components

## Diagram (Mermaid)

```mermaid
graph TB
    %% Actors and UI
    User["User (CLI / Streamlit UI)"]:::input
    User -->|invokes| Pipeline

    %% Configuration and Project Metadata
    Config["Configuration & Environment Loader"]:::storage
    Gitignore["Project Metadata & Exclusions"]:::storage
    User -->|reads docs| Config
    Config -->|provides configs| Pipeline
    User -->|initializes repo| Gitignore

    %% Core Pipeline Orchestrator
    Pipeline["Pipeline Manager"]:::core

    %% Sequential Pipeline Modules
    Pipeline -->|"loads audio"| Ingest
    Ingest["Audio Ingestion & Preprocessing"]:::core
    Ingest -->|audio streams| Diar

    Diar["Speaker Diarization"]:::core
    Diar -->|pure mode| Pure
    Diar -->|hybrid mode| Hybrid

    Pure["Pure pyannote-audio Mode"]:::core
    Hybrid["Hybrid WhisperX + pyannote-audio Mode"]:::core

    Pure -->|segments| ASR
    Hybrid -->|segments| ASR

    ASR["ASR Transcription (NVIDIA NeMo)"]:::core
    ASR -->|raw transcripts| Post

    Post["Post-Processing & Merging"]:::core
    Post -->|formatted data| Export

    Export["Output Exporters (.txt, .csv, .json, .srt/.vtt)"]:::io
    Export -->|writes to| LocalFS

    %% External Dependencies
    ExtModel["External Model Zoo (NVIDIA NeMo)"]:::external
    LocalFS["Local File System"]:::external
    Pipeline -->|requests models| ExtModel

    %% Legend
    subgraph Legend
        CP["Core Processing Modules"]:::core
        SC["Storage/Config"]:::storage
        IO["I/O Modules"]:::io
        EX["External Services"]:::external
    end

    %% Click Events
    click Config "https://github.com/prince1314-patel/multi-speaker-diarization/blob/main/README.md"
    click Gitignore "https://github.com/prince1314-patel/multi-speaker-diarization/blob/main/.gitignore"

    %% Styles
    classDef core fill:#bbdefb,stroke:#1e88e5,stroke-width:2px;
    classDef storage fill:#c8e6c9,stroke:#388e3c,stroke-width:2px;
    classDef io fill:#ffe0b2,stroke:#fb8c00,stroke-width:2px;
    classDef external fill:#e0e0e0,stroke:#757575,stroke-width:2px;
    classDef input fill:#f3e5f5,stroke:#8e24aa,stroke-width:2px;
```
