rixty/VoiceCraft
1
0
Fork 0
mirror of https://github.com/jasonppy/VoiceCraft.git synced 2025-02-17 04:00:52 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix number bug in whisperx alignment

Browse Source
This commit is contained in:
pyp_l40 2024-04-25 14:38:03 -05:00
parent 4a3a8f11a7
commit fd20265324
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
gradio_app.py
View File

@ -74,6 +74,8 @@ class WhisperxModel:
def transcribe(self, audio_path):
segments = self.model.transcribe(audio_path, batch_size=8)["segments"]
for segment in segments:
segment['text'] = replace_numbers_with_words(segment['text'])
return self.align_model.align(segments, audio_path)
@ -177,7 +179,7 @@ def align(seed, transcript, audio_path):
if align_model is None:
raise gr.Error("Align model not loaded")
seed_everything(seed)
transcript = replace_numbers_with_words(transcript).replace(" ", " ").replace(" ", " ")
fragments = align_segments(transcript, audio_path)
segments = [{
"start": float(fragment["begin"]),