Spaces:
Runtime error
Runtime error
File size: 1,301 Bytes
a9482ab 6ef16fa 7f6563e 6ef16fa 7f6563e a9482ab d2e0f91 91eda71 a9482ab |
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 |
import torch
import torchaudio
import torch.nn as nn
import torch.nn.functional as F
import IPython
import os
import subprocess
import sys
os.system("git clone https://github.com/neonbjb/tortoise-tts.git")
sys.path.append("tortoise-tts")
# entmax could not be installed at same time as torch
ubprocess.check_call([sys.executable, "-m", "pip", "install", "entmax"])
from api import TextToSpeech
from utils.audio import load_audio, get_voices
# This will download all the models used by Tortoise from the HF hub.
tts = TextToSpeech()
voices = [
"angie",
"daniel",
"deniro",
"emma",
"freeman",
"geralt",
"halle",
"jlaw",
"lj",
"snakes",
"tom",
"William",
]
voices = get_voices()
preset = "fastest"
def inference(text, voice):
cond_paths = voices[voice]
conds = []
for cond_path in cond_paths:
c = load_audio(cond_path, 22050)
conds.append(c)
gen = tts.tts_with_preset(text, conds, preset)
return gen
text = "Joining two modalities results in a surprising increase in generalization! What would happen if we combined them all?"
iface = gr.Interface(
generate_tone,
inputs=[
gr.inputs.Textbox(type="text", default=text, label="Text"),
gr.inputs.Dropdown(voices, type="index"),
],
outputs="audio",
)
iface.launch()
|