8139afd0e5
After training a similar model for a different purpose, I realized that this model is faulty: the contrastive loss it uses only pays attention to high-frequency details which do not contribute meaningfully to output quality. I validated this by comparing a no-CVVP output with a baseline using tts-scores and found no differences.
42 lines
2.6 KiB
Python
42 lines
2.6 KiB
Python
import argparse
|
|
import os
|
|
|
|
import torch
|
|
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="The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.")
|
|
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='random')
|
|
parser.add_argument('--preset', type=str, help='Which voice preset to use.', default='fast')
|
|
parser.add_argument('--output_path', type=str, help='Where to store outputs.', default='results/')
|
|
parser.add_argument('--model_dir', type=str, help='Where to find pretrained model checkpoints. Tortoise automatically downloads these to .models, so this'
|
|
'should only be specified if you have custom checkpoints.', default='.models')
|
|
parser.add_argument('--candidates', type=int, help='How many output candidates to produce per-voice.', default=3)
|
|
parser.add_argument('--seed', type=int, help='Random seed which can be used to reproduce results.', default=None)
|
|
parser.add_argument('--produce_debug_state', type=bool, help='Whether or not to produce debug_state.pth, which can aid in reproducing problems. Defaults to true.', default=True)
|
|
args = parser.parse_args()
|
|
os.makedirs(args.output_path, exist_ok=True)
|
|
|
|
tts = TextToSpeech(models_dir=args.model_dir)
|
|
|
|
selected_voices = args.voice.split(',')
|
|
for k, voice in enumerate(selected_voices):
|
|
voice_samples, conditioning_latents = load_voice(voice)
|
|
gen, dbg_state = tts.tts_with_preset(args.text, k=args.candidates, voice_samples=voice_samples, conditioning_latents=conditioning_latents,
|
|
preset=args.preset, use_deterministic_seed=args.seed, return_deterministic_state=True)
|
|
if isinstance(gen, list):
|
|
for j, g in enumerate(gen):
|
|
torchaudio.save(os.path.join(args.output_path, f'{voice}_{k}_{j}.wav'), g.squeeze(0).cpu(), 24000)
|
|
else:
|
|
torchaudio.save(os.path.join(args.output_path, f'{voice}_{k}.wav'), gen.squeeze(0).cpu(), 24000)
|
|
|
|
if args.produce_debug_state:
|
|
os.makedirs('debug_states', exist_ok=True)
|
|
torch.save(dbg_state, f'debug_states/do_tts_debug_{voice}.pth')
|
|
|