Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add back words-in-cue support #342

Merged
merged 1 commit into from
Dec 7, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions src/edge_tts/data_classes.py
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,7 @@ class UtilArgs(argparse.Namespace):
rate: str
volume: str
pitch: str
words_in_cue: int
write_media: str
write_subtitles: str
proxy: str
32 changes: 32 additions & 0 deletions src/edge_tts/submaker.py
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,38 @@ def feed(self, msg: TTSChunk) -> None:
)
)

def merge_cues(self, words: int) -> None:
"""
Merge cues to reduce the number of cues.

Args:
words (int): The number of words to merge.

Returns:
None
"""
if words <= 0:
raise ValueError("Invalid number of words to merge, expected > 0")

if len(self.cues) == 0:
return

new_cues: List[srt.Subtitle] = [] # type: ignore
current_cue: srt.Subtitle = self.cues[0] # type: ignore
for cue in self.cues[1:]:
if len(current_cue.content.split()) < words:
current_cue = srt.Subtitle(
index=current_cue.index,
start=current_cue.start,
end=cue.end,
content=current_cue.content + " " + cue.content,
)
else:
new_cues.append(current_cue)
current_cue = cue
new_cues.append(current_cue)
self.cues = new_cues

def get_srt(self) -> str:
"""
Get the SRT formatted subtitles from the SubMaker object.
Expand Down
9 changes: 9 additions & 0 deletions src/edge_tts/util.py
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,9 @@ async def _run_tts(args: UtilArgs) -> None:
elif chunk["type"] == "WordBoundary":
submaker.feed(chunk)

if args.words_in_cue > 0:
submaker.merge_cues(args.words_in_cue)

if sub_file is not None:
sub_file.write(submaker.get_srt())
finally:
Expand Down Expand Up @@ -107,6 +110,12 @@ async def amain() -> None:
parser.add_argument("--rate", help="set TTS rate. Default +0%%.", default="+0%")
parser.add_argument("--volume", help="set TTS volume. Default +0%%.", default="+0%")
parser.add_argument("--pitch", help="set TTS pitch. Default +0Hz.", default="+0Hz")
parser.add_argument(
"--words-in-cue",
help="number of words in a subtitle cue. Default: 10.",
default=10,
type=int,
)
parser.add_argument(
"--write-media", help="send media output to file instead of stdout"
)
Expand Down
Loading