aitist/flow.md
2024-08-04 11:23:57 -05:00

816 B

The AItist Listening Flow

(implementation outline: https://github.com/lablab-ai/Whisper-transcription_and_diarization-speaker-identification-/blob/main/transcribtion_diarization.ipynb

flowchart TD
    subgraph "Context Input"
    record[\VAD/] --> transcribe
    record --> diarize
    diarize --> identify_speakers
    identify_speakers --> regard{{Do speakers matter}}
    transcribe --> regard
    regard --yes--> parse_context
    regard --"no"--> stop[/Stop\]
    regard --some--> log_speakers
    log_speakers --> parse_context
    parse_context --> known{{Context known}}
    known --"no"--> log_context[Log for async analysis]
    end

    subgraph Process
        known --yes--> apply_context_prompt
        apply_context_prompt --> llm_find_action["Find action from text"]
    end