forked from mrq/tortoise-tts
8fdf516e62
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.
75 lines
3.7 KiB
Python
75 lines
3.7 KiB
Python
import argparse
|
|
import os
|
|
from time import time
|
|
|
|
import torch
|
|
import torchaudio
|
|
|
|
from api import TextToSpeech
|
|
from utils.audio import load_audio, get_voices, load_voices
|
|
from utils.text import split_and_recombine_text
|
|
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--textfile', type=str, help='A file containing the text to read.', default="tortoise/data/riding_hood.txt")
|
|
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('--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('--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('--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()
|
|
tts = TextToSpeech(models_dir=args.model_dir)
|
|
|
|
outpath = args.output_path
|
|
selected_voices = args.voice.split(',')
|
|
regenerate = args.regenerate
|
|
if regenerate is not None:
|
|
regenerate = [int(e) for e in regenerate.split(',')]
|
|
|
|
# Process text
|
|
with open(args.textfile, 'r', encoding='utf-8') as f:
|
|
text = ' '.join([l for l in f.readlines()])
|
|
if '|' in text:
|
|
print("Found the '|' character in your text, which I will use as a cue for where to split it up. If this was not"
|
|
"your intent, please remove all '|' characters from the input.")
|
|
texts = text.split('|')
|
|
else:
|
|
texts = split_and_recombine_text(text)
|
|
|
|
seed = int(time()) if args.seed is None else args.seed
|
|
for selected_voice in selected_voices:
|
|
voice_outpath = os.path.join(outpath, selected_voice)
|
|
os.makedirs(voice_outpath, exist_ok=True)
|
|
|
|
if '&' in selected_voice:
|
|
voice_sel = selected_voice.split('&')
|
|
else:
|
|
voice_sel = [selected_voice]
|
|
|
|
voice_samples, conditioning_latents = load_voices(voice_sel)
|
|
all_parts = []
|
|
for j, text in enumerate(texts):
|
|
if regenerate is not None and j not in regenerate:
|
|
all_parts.append(load_audio(os.path.join(voice_outpath, f'{j}.wav'), 24000))
|
|
continue
|
|
gen = tts.tts_with_preset(text, voice_samples=voice_samples, conditioning_latents=conditioning_latents,
|
|
preset=args.preset, use_deterministic_seed=seed)
|
|
gen = gen.squeeze(0).cpu()
|
|
torchaudio.save(os.path.join(voice_outpath, f'{j}.wav'), gen, 24000)
|
|
all_parts.append(gen)
|
|
|
|
full_audio = torch.cat(all_parts, dim=-1)
|
|
torchaudio.save(os.path.join(voice_outpath, 'combined.wav'), full_audio, 24000)
|
|
|
|
if args.produce_debug_state:
|
|
os.makedirs('debug_states', exist_ok=True)
|
|
dbg_state = (seed, texts, voice_samples, conditioning_latents)
|
|
torch.save(dbg_state, f'debug_states/read_debug_{selected_voice}.pth')
|
|
|