neonbjb/tortoise-tts
1
0
Fork 0
mirror of https://github.com/neonbjb/tortoise-tts.git synced 2026-01-04 07:40:02 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #405 from narviii/output-name

Browse source 
output filename in args
This commit is contained in:
manmay nakhashi 2023-07-27 00:01:31 +05:30 committed by GitHub
parent f13955db54 796ceac1a4
commit 614bc9d761
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
tortoise/read.py
View file

@ -16,6 +16,7 @@ if __name__ == '__main__':
parser.add_argument('--voice', type=str, help='Selects the voice to use for generation. See options in voices/ directory (and add your own!) '
'Use the & character to join two voices together. Use a comma to perform inference on multiple voices.', default='pat')
parser.add_argument('--output_path', type=str, help='Where to store outputs.', default='results/longform/')
parser.add_argument('--output_name', type=str, help='How to name the output file', default='combined.wav')
parser.add_argument('--preset', type=str, help='Which voice preset to use.', default='standard')
parser.add_argument('--regenerate', type=str, help='Comma-separated list of clip numbers to re-generate, or nothing.', default=None)
parser.add_argument('--candidates', type=int, help='How many output candidates to produce per-voice. Only the first candidate is actually used in the final product, the others can be used manually.', default=1)
@ -28,6 +29,7 @@ if __name__ == '__main__':
tts = TextToSpeech(models_dir=args.model_dir)
outpath = args.output_path
outname = args.output_name
selected_voices = args.voice.split(',')
regenerate = args.regenerate
if regenerate is not None:
@ -74,7 +76,7 @@ if __name__ == '__main__':
if args.candidates == 1:
full_audio = torch.cat(all_parts, dim=-1)
torchaudio.save(os.path.join(voice_outpath, 'combined.wav'), full_audio, 24000)
torchaudio.save(os.path.join(voice_outpath, f"{outname}.wav"), full_audio, 24000)
if args.produce_debug_state:
os.makedirs('debug_states', exist_ok=True)
@ -89,5 +91,5 @@ if __name__ == '__main__':
wav_file = os.path.join(voice_outpath, str(line), f"{candidate}.wav")
audio_clips.append(load_audio(wav_file, 24000))
audio_clips = torch.cat(audio_clips, dim=-1)
torchaudio.save(os.path.join(voice_outpath, f"combined_{candidate:02d}.wav"), audio_clips, 24000)
torchaudio.save(os.path.join(voice_outpath, f"{outname}_{candidate:02d}.wav"), audio_clips, 24000)
audio_clips = []