42 lines
845 B
Python
42 lines
845 B
Python
"""Datenmodelle fuer Transkriptionsergebnisse."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
|
|
|
|
@dataclass
|
|
class WordToken:
|
|
"""Ein Wort mit Zeitstempel aus Whisper."""
|
|
|
|
word: str
|
|
start: float
|
|
end: float
|
|
probability: float | None = None
|
|
|
|
|
|
@dataclass
|
|
class TranscriptSegment:
|
|
"""Ein Whisper-Segment."""
|
|
|
|
text: str
|
|
start: float
|
|
end: float
|
|
confidence: float | None = None
|
|
words: list[WordToken] = field(default_factory=list)
|
|
|
|
|
|
@dataclass
|
|
class TranscriptResult:
|
|
"""Vollstaendiges Transkript einer Audiodatei."""
|
|
|
|
segments: list[TranscriptSegment]
|
|
full_text: str
|
|
language: str | None = None
|
|
language_probability: float | None = None
|
|
duration: float | None = None
|
|
model: str = ""
|
|
|
|
def __len__(self) -> int:
|
|
return len(self.segments)
|