From e92325b7eb03583f53f8c6d19d2ce7f7122aa344 Mon Sep 17 00:00:00 2001 From: Ahmad Bilal Date: Thu, 20 Jul 2023 03:19:37 +0500 Subject: [PATCH] Remove the fix --- whisperx/diarize.py | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/whisperx/diarize.py b/whisperx/diarize.py index 59ca9e2..b14addf 100644 --- a/whisperx/diarize.py +++ b/whisperx/diarize.py @@ -27,8 +27,6 @@ class DiarizationPipeline: def assign_word_speakers(diarize_df, transcript_result, fill_nearest=False): transcript_segments = transcript_result["segments"] for seg in transcript_segments: - if 'text' in seg: - seg["text"] = seg["text"].replace('"', "'") # assign speaker to segment (if any) diarize_df['intersection'] = np.minimum(diarize_df['end'], seg['end']) - np.maximum(diarize_df['start'], seg['start']) @@ -46,7 +44,7 @@ def assign_word_speakers(diarize_df, transcript_result, fill_nearest=False): # assign speaker to words if 'words' in seg: for word in seg['words']: - word["word"] = word["word"].replace('"', "'") + if 'start' in word: diarize_df['intersection'] = np.minimum(diarize_df['end'], word['end']) - np.maximum(diarize_df['start'], word['start']) diarize_df['union'] = np.maximum(diarize_df['end'], word['end']) - np.minimum(diarize_df['start'], word['start'])