Spaces:
Running
on
Zero
Running
on
Zero
File size: 2,393 Bytes
9d593b2 2e214c5 9d593b2 2e214c5 9d593b2 2e214c5 9d593b2 2e214c5 9d593b2 f094d94 58ffee2 2bd4215 58ffee2 9d593b2 2e214c5 9d593b2 58ffee2 9d593b2 2e214c5 9d593b2 fae012e |
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 |
import random
import numpy as np
import torch
from chatterbox.src.chatterbox.tts import ChatterboxTTS
import gradio as gr
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
def set_seed(seed: int):
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
random.seed(seed)
np.random.seed(seed)
def load_model():
return ChatterboxTTS.from_pretrained(DEVICE)
def generate(model, text, audio_prompt_path, exaggeration, pace, temperature, seed_num, cfgw):
if model is None:
model = ChatterboxTTS.from_pretrained(DEVICE)
if seed_num != 0:
set_seed(int(seed_num))
wav = model.generate(
text,
audio_prompt_path=audio_prompt_path,
exaggeration=exaggeration,
pace=pace,
temperature=temperature,
cfg_weight=cfgw,
)
return (model, (model.sr, wav.squeeze(0).numpy()))
with gr.Blocks() as demo:
model_state = gr.State(None) # Loaded once per session/user
with gr.Row():
with gr.Column():
text = gr.Textbox(value="What does the fox say?", label="Text to synthesize")
ref_wav = gr.Audio(sources=["upload", "microphone"], type="filepath", label="Reference Audio File", value="https://storage.googleapis.com/chatterbox-demo-samples/prompts/wav7604828.wav")
exaggeration = gr.Slider(0.25, 2, step=.05, label="Exaggeration (Neutral = 0.5, extreme values can be unstable)", value=.5)
cfg_weight = gr.Slider(0.2, 1, step=.05, label="CFG/Pace", value=0.5)
with gr.Accordion("More options", open=False):
seed_num = gr.Number(value=0, label="Random seed (0 for random)")
temp = gr.Slider(0.05, 5, step=.05, label="temperature", value=.8)
pace = gr.Slider(0.8, 1.2, step=.01, label="pace", value=1)
run_btn = gr.Button("Generate", variant="primary")
with gr.Column():
audio_output = gr.Audio(label="Output Audio")
run_btn.click(
fn=generate,
inputs=[
model_state,
text,
ref_wav,
exaggeration,
pace,
temp,
seed_num,
cfg_weight,
],
outputs=[model_state, audio_output],
)
demo.queue(
max_size=50,
default_concurrency_limit=1,
).launch(share=True)
|