File size: 925 Bytes
5d8ba63 2d1af42 55a312f 2d1af42 55a312f 2d1af42 55a312f 2d1af42 55a312f eb0d07d |
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 |
import gradio as gr
from transformers import BarkModel, AutoProcessor
import torch
import scipy.io.wavfile as wav
# Load Bark model
processor = AutoProcessor.from_pretrained("suno/bark")
model = BarkModel.from_pretrained("suno/bark")
def generate(text):
if not text:
return None
inputs = processor(text, return_tensors="pt")
audio = model.generate(**inputs)
audio = audio.cpu().numpy().squeeze()
output_path = "output.wav"
wav.write(output_path, 22050, audio)
return output_path
demo = gr.Interface(
fn=generate,
inputs=gr.Textbox(
label="Text",
placeholder="Type something to speak..."
),
outputs=gr.Audio(
label="AI Voice",
type="filepath"
),
title="AI Voice Generator (HF Stable)",
description="Hugging Face compatible AI voice generator"
)
demo.launch(
server_name="0.0.0.0",
server_port=7860,
share=False
) |