Spaces:
Sleeping
Sleeping
File size: 4,751 Bytes
de41fea d7c3a35 de41fea d7c3a35 de41fea 3a8be35 de41fea 3a8be35 de41fea 3a8be35 de41fea 3a8be35 de41fea 3a8be35 de41fea 3a8be35 de41fea 3a8be35 de41fea |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 |
import os
import gradio as gr
import outetts
from outetts.version.v2.interface import DEFAULT_SPEAKERS # Fixed the import syntax
import torch
import spaces
def get_available_speakers():
speakers = list(DEFAULT_SPEAKERS.keys()) # Fixed variable name
return speakers
@spaces.GPU
def generate_tts(text, temperature, repetition_penalty, speaker_selection, reference_audio):
model_config = outetts.HFModelConfig_v2(
model_path="OuteAI/OuteTTS-0.3-1B",
tokenizer_path="OuteAI/OuteTTS-0.3-1B",
dtype=torch.bfloat16,
device="cuda"
)
interface = outetts.InterfaceHF(model_version="0.3", cfg=model_config)
try:
if reference_audio:
speaker = interface.create_speaker(reference_audio)
elif speaker_selection and speaker_selection != "None":
speaker = interface.load_default_speaker(speaker_selection)
else:
speaker = None
gen_cfg = outetts.GenerationConfig(
text=text,
temperature=temperature,
repetition_penalty=repetition_penalty,
max_length=4096,
speaker=speaker,
)
output = interface.generate(config=gen_cfg)
if output.audio is None:
raise ValueError("Audio generation failed. Please try again.")
output_path = "output.wav"
output.save(output_path)
return output_path, None
except Exception as e:
return None, str(e)
# Custom CSS for 3D effect and modern UI
custom_css = """
.container {
background: linear-gradient(145deg, #f0f0f0, #ffffff);
border-radius: 20px;
box-shadow: 20px 20px 60px #bebebe, -20px -20px 60px #ffffff;
padding: 2rem;
}
.title {
font-size: 2.5rem;
text-align: center;
background: linear-gradient(45deg, #2196F3, #00BCD4);
-webkit-background-clip: text;
-webkit-text-fill-color: transparent;
margin-bottom: 2rem;
}
.radio-group {
display: grid;
grid-template-columns: repeat(auto-fill, minmax(150px, 1fr));
gap: 1rem;
margin: 1rem 0;
}
.control-panel {
background: rgba(255, 255, 255, 0.9);
border-radius: 15px;
padding: 1.5rem;
margin: 1rem 0;
}
"""
with gr.Blocks(css=custom_css) as demo:
with gr.Column(elem_classes="container"):
gr.Markdown("# Voice Clone Multilingual TTS", elem_classes="title")
with gr.Row():
with gr.Column(scale=2):
# Main input section with 3D effect
with gr.Group(elem_classes="control-panel"):
text_input = gr.Textbox(
label="Enter Text",
placeholder="Type your text here...",
lines=3
)
speaker_radio = gr.Radio(
choices=get_available_speakers(),
value="en_male_1",
label="Choose Voice",
elem_classes="radio-group"
)
with gr.Row():
temperature = gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.1,
label="Expression Level"
)
repetition_penalty = gr.Slider(
minimum=0.5,
maximum=2.0,
value=1.1,
label="Clarity"
)
reference_audio = gr.Audio(
label="Upload Voice Reference",
type="filepath"
)
submit_button = gr.Button(
"Generate Speech",
variant="primary"
)
with gr.Column(scale=1):
# Output section
audio_output = gr.Audio(
label="Generated Audio",
type="filepath"
)
error_box = gr.Textbox(
label="Status",
visible=False
)
submit_button.click(
fn=generate_tts,
inputs=[
text_input,
temperature,
repetition_penalty,
speaker_radio,
reference_audio,
],
outputs=[audio_output, error_box]
).then(
fn=lambda x: gr.update(visible=bool(x)),
inputs=[error_box],
outputs=[error_box]
)
demo.launch() |