mrq/ai-voice-cloning
31
74
Fork 43
Code Issues 223 Pull Requests 5 Packages Projects Releases Wiki Activity

when the sanitizer thingy works in testing but it doesn't outside of testing, and you have to retranscribe for the fourth time today

Browse Source
This commit is contained in:
mrq 2023-03-23 02:37:44 +00:00
parent 86589fff91
commit a6daf289bc
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/utils.py
View File

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