Spaces:
Running
Running
File size: 3,302 Bytes
70fee89 506a2b4 70fee89 506a2b4 d9e30fc 506a2b4 |
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 |
import sys
import os
sys.path.append(os.path.join(os.path.dirname(__file__), "src"))
import random
import numpy as np
import torch
import gradio as gr
from chatterbox.tts import ChatterboxTTS
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():
model = ChatterboxTTS.from_pretrained(DEVICE)
return model
def generate(model, text, audio_prompt_path, exaggeration, temperature, seed_num, cfgw, min_p, top_p, repetition_penalty):
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,
temperature=temperature,
cfg_weight=cfgw,
min_p=min_p,
top_p=top_p,
repetition_penalty=repetition_penalty,
)
return (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="Now let's make my mum's favourite. So three mars bars into the pan. Then we add the tuna and just stir for a bit, just let the chocolate and fish infuse. A sprinkle of olive oil and some tomato ketchup. Now smell that. Oh boy this is going to be incredible.",
label="Text to synthesize (max chars 300)",
max_lines=5
)
ref_wav = gr.Audio(sources=["upload", "microphone"], type="filepath", label="Reference Audio File", value=None)
exaggeration = gr.Slider(0.25, 2, step=.05, label="Exaggeration (Neutral = 0.5, extreme values can be unstable)", value=.5)
cfg_weight = gr.Slider(0.0, 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)
min_p = gr.Slider(0.00, 1.00, step=0.01, label="min_p || Newer Sampler. Recommend 0.02 > 0.1. Handles Higher Temperatures better. 0.00 Disables", value=0.05)
top_p = gr.Slider(0.00, 1.00, step=0.01, label="top_p || Original Sampler. 1.0 Disables(recommended). Original 0.8", value=1.00)
repetition_penalty = gr.Slider(1.00, 2.00, step=0.1, label="repetition_penalty", value=1.2)
run_btn = gr.Button("Generate", variant="primary")
with gr.Column():
audio_output = gr.Audio(label="Output Audio")
demo.load(fn=load_model, inputs=[], outputs=model_state)
run_btn.click(
fn=generate,
inputs=[
model_state,
text,
ref_wav,
exaggeration,
temp,
seed_num,
cfg_weight,
min_p,
top_p,
repetition_penalty,
],
outputs=audio_output,
)
if __name__ == "__main__":
demo.queue(
max_size=50,
default_concurrency_limit=1,
).launch(share=True)
|