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

Merge pull request #440 from jim60105/main

Browse Source 
chore(writer): Join words without spaces for ja, zh
This commit is contained in:
Max Bain
2023-08-29 11:22:30 -06:00
committed by GitHub
parent adf455a97c 5223de2a41
commit 8c4a21b66d
2 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
whisperx/transcribe.py
View File

@ -118,6 +118,7 @@ def cli():
f"{model_name} is an English-only model but receipted '{args['language']}'; using English instead." f"{model_name} is an English-only model but receipted '{args['language']}'; using English instead."
) )
args["language"] = "en" args["language"] = "en"
align_language = args["language"] if args["language"] is not None else "en" # default to loading english if not specified
temperature = args.pop("temperature") temperature = args.pop("temperature")
if (increment := args.pop("temperature_increment_on_fallback")) is not None: if (increment := args.pop("temperature_increment_on_fallback")) is not None:
@ -174,7 +175,6 @@ def cli():
if not no_align: if not no_align:
tmp_results = results tmp_results = results
results = [] results = []
align_language = args["language"] if args["language"] is not None else "en" # default to loading english if not specified
align_model, align_metadata = load_align_model(align_language, device, model_name=align_model) align_model, align_metadata = load_align_model(align_language, device, model_name=align_model)
for result, audio_path in tmp_results: for result, audio_path in tmp_results:
# >> Align # >> Align
@ -213,6 +213,7 @@ def cli():
results.append((result, input_audio_path)) results.append((result, input_audio_path))
# >> Write # >> Write
for result, audio_path in results: for result, audio_path in results:
result["language"] = align_language
writer(result, audio_path, writer_args) writer(result, audio_path, writer_args)
if __name__ == "__main__": if __name__ == "__main__":

4
whisperx/utils.py
View File

@ -123,6 +123,7 @@ TO_LANGUAGE_CODE = {
"castilian": "es", "castilian": "es",
} }
LANGUAGES_WITHOUT_SPACES = ["ja", "zh"]
system_encoding = sys.getdefaultencoding() system_encoding = sys.getdefaultencoding()
@ -283,6 +284,9 @@ class SubtitlesWriter(ResultWriter):
sstart, ssend, speaker = _[0] sstart, ssend, speaker = _[0]
subtitle_start = self.format_timestamp(sstart) subtitle_start = self.format_timestamp(sstart)
subtitle_end = self.format_timestamp(ssend) subtitle_end = self.format_timestamp(ssend)
if result["language"] in LANGUAGES_WITHOUT_SPACES:
subtitle_text = "".join([word["word"] for word in subtitle])
else:
subtitle_text = " ".join([word["word"] for word in subtitle]) subtitle_text = " ".join([word["word"] for word in subtitle])
has_timing = any(["start" in word for word in subtitle]) has_timing = any(["start" in word for word in subtitle])