Spaces:
Runtime error
Runtime error
File size: 3,522 Bytes
ee04bc2 |
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 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 |
import argparse
import os
import torch
import torchaudio
from api import TextToSpeech, MODELS_DIR
from utils.audio import load_voices
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_DIR,
)
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,
)
parser.add_argument(
"--cvvp_amount",
type=float,
help="How much the CVVP model should influence the output."
"Increasing this can in some cases reduce the likelyhood of multiple speakers. Defaults to 0 (disabled)",
default=0.0,
)
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, selected_voice in enumerate(selected_voices):
if "&" in selected_voice:
voice_sel = selected_voice.split("&")
else:
voice_sel = [selected_voice]
voice_samples, conditioning_latents = load_voices(voice_sel)
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,
cvvp_amount=args.cvvp_amount,
)
if isinstance(gen, list):
for j, g in enumerate(gen):
torchaudio.save(
os.path.join(args.output_path, f"{selected_voice}_{k}_{j}.wav"),
g.squeeze(0).cpu(),
24000,
)
else:
torchaudio.save(
os.path.join(args.output_path, f"{selected_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_{selected_voice}.pth")
|