models.py

"""Data models for the Audio Labeling Tool."""

from dataclasses import dataclass
from typing import TypedDict


class LabelRow(TypedDict):
    """TypedDict representing a single row in the metadata CSV."""

    source: str  # Audio filename only (e.g., "clip_001.wav")
    transcription: str  # Corrected transcription text
    gender: str  # "male" or "female"
    pii: str  # "True" or "False" (string representation in CSV)
    labeler: str  # Username of the labeler


@dataclass
class LabelRecord:
    """Dataclass for constructing a label before saving."""

    source: str
    transcription: str
    gender: str
    pii: bool
    labeler: str