time objects is now used by DiartDiarization class
Browse files- timed_objects.py +27 -0
timed_objects.py
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from dataclasses import dataclass
|
| 2 |
+
from typing import Optional
|
| 3 |
+
|
| 4 |
+
@dataclass
|
| 5 |
+
class TimedText:
|
| 6 |
+
start: Optional[float]
|
| 7 |
+
end: Optional[float]
|
| 8 |
+
text: Optional[str] = ''
|
| 9 |
+
speaker: Optional[int] = -1
|
| 10 |
+
|
| 11 |
+
@dataclass
|
| 12 |
+
class ASRToken(TimedText):
|
| 13 |
+
def with_offset(self, offset: float) -> "ASRToken":
|
| 14 |
+
"""Return a new token with the time offset added."""
|
| 15 |
+
return ASRToken(self.start + offset, self.end + offset, self.text)
|
| 16 |
+
|
| 17 |
+
@dataclass
|
| 18 |
+
class Sentence(TimedText):
|
| 19 |
+
pass
|
| 20 |
+
|
| 21 |
+
@dataclass
|
| 22 |
+
class Transcript(TimedText):
|
| 23 |
+
pass
|
| 24 |
+
|
| 25 |
+
@dataclass
|
| 26 |
+
class SpeakerSegment(TimedText):
|
| 27 |
+
pass
|