refactor: converter methods do not need to ingest segments

capgen/transcriber/converter.py

@@ -2,8 +2,6 @@
 
 from faster_whisper.transcribe import Segment
 
-from capgen.utils import convert_seconds_to_hhmmssmmm
-
 
 class Converter:
     """
@@ -17,17 +15,42 @@ class Converter:
 
     Methods
     -------
-    convert_seconds_to_hhmmssmmm(seconds: float) -> str:
+    convert_seconds_to_hhmmssmmm(seconds: float, millisecond_separator: str) -> str:
         converts seconds to hh:mm:ss,mmm format
 
-    as_srt(segments: Iterable[Segment]) -> str:
+    to_srt() -> str:
         converts transcription segments into a SRT file
+
+    to_vtt() -> str:
+        converts transcription segments into a VTT file
     """
 
+    __slots__ = ('segments',)
+
     def __init__(self, segments: Iterable[Segment]):
         self.segments = segments
 
-    def to_srt(self, segments: Iterable[Segment]) -> str:
+    def convert_seconds_to_hhmmssmmm(self, seconds: float, millisecond_separator: str) -> str:
+        """
+        Summary
+        -------
+        converts seconds to hh:mm:ss,mmm format
+
+        Parameters
+        ----------
+        seconds (float) : the number of seconds to convert
+
+        Returns
+        -------
+        converted_time (str) : the converted time in hh:mm:ss,mmm format
+        """
+        hours, remainder = divmod(seconds, 3600)
+        minutes, seconds = divmod(remainder, 60)
+        milliseconds = int((seconds % 1) * 1000)
+
+        return f'{int(hours):02}:{int(minutes):02}:{int(seconds):02}{millisecond_separator}{milliseconds:03}'
+
+    def to_srt(self) -> str:
         """
         Summary
         -------
@@ -42,13 +65,13 @@ def to_srt(self, segments: Iterable[Segment]) -> str:
         subrip_subtitle (str) : the SRT subtitles
         """
         return '\n\n'.join(
-            f'{segment.id}\n'
-            f'{convert_seconds_to_hhmmssmmm(segment.start, ",")} --> '
-            f'{convert_seconds_to_hhmmssmmm(segment.end, ",")}\n{segment.text[1:]}'
-            for segment in segments
+            f'{id}\n'
+            f'{self.convert_seconds_to_hhmmssmmm(start, ",")} --> '
+            f'{self.convert_seconds_to_hhmmssmmm(end, ",")}\n{text[1:]}'
+            for id, _, start, end, text, *_ in self.segments
         )
 
-    def to_vtt(self, segments: Iterable[Segment]) -> str:
+    def to_vtt(self) -> str:
         """
         Summary
         -------
@@ -63,9 +86,9 @@ def to_vtt(self, segments: Iterable[Segment]) -> str:
         video_text_tracks_subtitle (str) : the VTT subtitles
         """
         captions = '\n\n'.join(
-            f'{convert_seconds_to_hhmmssmmm(segment.start, ".")} --> '
-            f'{convert_seconds_to_hhmmssmmm(segment.end, ".")}\n{segment.text[1:]}'
-            for segment in segments
+            f'{self.convert_seconds_to_hhmmssmmm(start, ".")} --> '
+            f'{self.convert_seconds_to_hhmmssmmm(end, ".")}\n{text[1:]}'
+            for _, _, start, end, text, *_ in self.segments
         )
 
         return f'WEBVTT\n\n{captions}'

capgen/transcriber/transcriber.py

@@ -79,9 +79,9 @@ def transcribe(self, file: str | BinaryIO, caption_format: str) -> str | None:
         converter = Converter(segments)
 
         if caption_format == 'srt':
-            return converter.to_srt(segments)
+            return converter.to_srt()
 
         if caption_format == 'vtt':
-            return converter.to_vtt(segments)
+            return converter.to_vtt()
 
         return None