From a6daf289bcf2c9f66fbbb75e4dac5ca2b46c1fd8 Mon Sep 17 00:00:00 2001
From: mrq <mrq@ecker.tech>
Date: Thu, 23 Mar 2023 02:37:44 +0000
Subject: [PATCH] when the sanitizer thingy works in testing but it doesn't
 outside of testing, and you have to retranscribe for the fourth time today

---
 src/utils.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/utils.py b/src/utils.py
index 43cb78d..668d696 100755
--- a/src/utils.py
+++ b/src/utils.py
@@ -1294,6 +1294,7 @@ def transcribe_dataset( voice, language=None, skip_existings=False, progress=Non
 				continue
 			results[basename] = result
 
+		"""
 		try:
 			sanitized = whisper_sanitize(results[basename])
 			if len(sanitized['segments']) > 0 and len(sanitized['segments']) != len(results[basename]['segments']):
@@ -1303,6 +1304,7 @@ def transcribe_dataset( voice, language=None, skip_existings=False, progress=Non
 		except Exception as e:
 			print("Failed to sanitize:", basename, e)
 			pass
+		"""
 
 		waveform, sample_rate = torchaudio.load(file)
 		# resample to the input rate, since it'll get resampled for training anyways