chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

.wav conversion, handle audio with no detected speech

Browse Source
This commit is contained in:
Max Bain
2023-03-31 23:02:38 +01:00
parent d0fa028045
commit b9ca701d69
5 changed files with 50 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
whisperx/utils.py
View File

@ -270,6 +270,8 @@ class WriteSRTWord(ResultWriter):
yield segment_start, segment_end, segment_text
def write_result(self, result: dict, file: TextIO):
if "word_segments" not in result:
return
for i, (start, end, text) in enumerate(self.iterate_result(result), start=1):
print(f"{i}\n{start} --> {end}\n{text}\n", file=file, flush=True)
@ -286,11 +288,16 @@ def get_writer(output_format: str, output_dir: str) -> Callable[[dict, TextIO],
"vtt": WriteVTT,
"srt": WriteSRT,
"tsv": WriteTSV,
# "json": WriteJSON,
"ass": WriteASS,
"srt-word": WriteSRTWord,
# "ass-char": WriteASSchar,
# "pickle": WritePickle,
"srt-word": WriteSRTWord,
# "json": WriteJSON,
}
writers_other = {
"pkl": WritePickle,
"ass-char": WriteASSchar
}
if output_format == "all":
@ -302,4 +309,9 @@ def get_writer(output_format: str, output_dir: str) -> Callable[[dict, TextIO],
return write_all
return writers[output_format](output_dir)
if output_format in writers:
return writers[output_format](output_dir)
elif output_format in writers_other:
return writers_other[output_format](output_dir)
else:
raise ValueError(f"Output format '{output_format}' not supported, choose from {writers.keys()} and {writers_other.keys()}")