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

forgot to try and have it try and auto-detect for openai/whisper when no language is specified

Browse Source
This commit is contained in:
mrq 2023-03-05 05:22:35 +00:00
parent 3e220ed306
commit 1316331be3
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/utils.py
View File

@ -941,6 +941,9 @@ def whisper_transcribe( file, language=None ):
load_whisper_model(language=language) load_whisper_model(language=language)
if not args.whisper_cpp: if not args.whisper_cpp:
if not language:
language = None
return whisper_model.transcribe(file, language=language) return whisper_model.transcribe(file, language=language)
res = whisper_model.transcribe(file) res = whisper_model.transcribe(file)
@ -998,12 +1001,13 @@ def prepare_dataset( files, outdir, language=None, progress=None ):
with open(f'{outdir}/whisper.json', 'w', encoding="utf-8") as f: with open(f'{outdir}/whisper.json', 'w', encoding="utf-8") as f:
f.write(json.dumps(results, indent='\t')) f.write(json.dumps(results, indent='\t'))
joined = '\n'.join(transcription)
with open(f'{outdir}/train.txt', 'w', encoding="utf-8") as f: with open(f'{outdir}/train.txt', 'w', encoding="utf-8") as f:
f.write("\n".join(transcription)) f.write(joined)
unload_whisper() unload_whisper()
return f"Processed dataset to: {outdir}" return f"Processed dataset to: {outdir}\n{joined}"
def calc_iterations( epochs, lines, batch_size ): def calc_iterations( epochs, lines, batch_size ):
iterations = int(epochs * lines / float(batch_size)) iterations = int(epochs * lines / float(batch_size))