File size: 1,752 Bytes
5a958b4 1a2fb5d fc8d52a 0ffc191 1a2fb5d 5a958b4 c52cc78 fc8d52a b9a534a 8696bb4 c52cc78 5a958b4 287debd 39ab8a9 5a958b4 fc8d52a 0ffc191 287debd c66954b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 |
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)
|