graph TD A[Input WAV File] --> B[Tempo Analysis] A --> C[Stem Separation] B --> B1[Detect Tempo] B1 --> B2[Extract Beatpoints] B2 --> B3[Generate Tempo Data] B3 --> D[tempo_beatpoint_data.json] C --> C1[ML Stem Separation] C1 --> C2[Raw Stems] C2 --> C3[Convert to WAV Format] C3 --> E[instrumental.wav] C3 --> F[vocals.wav] D --> G[Final Output Package] E --> G F --> G style A fill:#f9f,stroke:#333 style G fill:#9ff,stroke:#333