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

forgot to re-append the existing transcription when skipping existing (have to go back again and do the first 10% of my giant dataset

Browse Source
This commit is contained in:
mrq 2023-03-06 16:50:55 +00:00
parent da0af4c498
commit 119ac50c58
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/utils.py
View File

@ -1057,8 +1057,8 @@ def prepare_dataset( files, outdir, language=None, skip_existings=False, progres
files = sorted(files)
previous_list = []
if skip_existings and os.path.exists(f'{outdir}/train.txt'):
parsed_list = []
if skip_existings and os.path.exists(f'{outdir}/train.txt'):
with open(f'{outdir}/train.txt', 'r', encoding="utf-8") as f:
parsed_list = f.readlines()
@ -1110,6 +1110,9 @@ def prepare_dataset( files, outdir, language=None, skip_existings=False, progres
with open(f'{outdir}/whisper.json', 'w', encoding="utf-8") as f:
f.write(json.dumps(results, indent='\t'))
if len(parsed_list) > 0:
transcription = parsed_list + transcription
joined = '\n'.join(transcription)
with open(f'{outdir}/train.txt', 'w', encoding="utf-8") as f:
f.write(joined)