forked from mrq/tortoise-tts
01b783fc02
- Adds a new script and API endpoints for doing this - Reworks autoregressive and diffusion models so that the conditioning is computed separately (which will actually provide a mild performance boost) - Updates README This is untested. Need to do the following manual tests (and someday write unit tests for this behemoth before it becomes a problem..) 1) Does get_conditioning_latents.py work? 2) Can I feed those latents back into the model by creating a new voice? 3) Can I still mix and match voices (both with conditioning latents and normal voices) with read.py?
31 lines
1.7 KiB
Python
31 lines
1.7 KiB
Python
import argparse
|
|
import os
|
|
|
|
import torchaudio
|
|
|
|
from api import TextToSpeech
|
|
from tortoise.utils.audio import load_audio, get_voices, load_voice
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--text', type=str, help='Text to speak.', default="I am a language model that has learned to speak.")
|
|
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('--preset', type=str, help='Which voice preset to use.', default='standard')
|
|
parser.add_argument('--voice_diversity_intelligibility_slider', type=float,
|
|
help='How to balance vocal diversity with the quality/intelligibility of the spoken text. 0 means highly diverse voice (not recommended), 1 means maximize intellibility',
|
|
default=.5)
|
|
parser.add_argument('--output_path', type=str, help='Where to store outputs.', default='results/')
|
|
args = parser.parse_args()
|
|
os.makedirs(args.output_path, exist_ok=True)
|
|
|
|
tts = TextToSpeech()
|
|
|
|
selected_voices = args.voice.split(',')
|
|
for voice in selected_voices:
|
|
voice_samples, conditioning_latents = load_voice(voice)
|
|
gen = tts.tts_with_preset(args.text, voice_samples=voice_samples, conditioning_latents=conditioning_latents,
|
|
preset=args.preset, clvp_cvvp_slider=args.voice_diversity_intelligibility_slider)
|
|
torchaudio.save(os.path.join(args.output_path, f'{voice}.wav'), gen.squeeze(0).cpu(), 24000)
|
|
|