File size: 2,615 Bytes
850343e f626de0 850343e f626de0 850343e |
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 |
# import gradio as gr
from ultralytics import YOLO
model = YOLO('yolo11n-pose.pt')
def poseImage(image):
results = model(image)
return results[0].plot()
# interface = gr.Interface(
# fn=poseImage,
# inputs=gr.Image(streaming=True),
# outputs=gr.Image(),
# live=True
# )
# interface.launch()
import gradio as gr
import speech_recognition as sr
from PIL import Image
# Fungsi untuk memproses gambar
def process_image(image):
return image # Mengembalikan gambar yang sama
# Fungsi untuk memproses audio
def process_audio(audio):
recognizer = sr.Recognizer()
with sr.AudioFile(audio) as source:
audio_data = recognizer.record(source)
try:
text = recognizer.recognize_google(audio_data)
return text
except sr.UnknownValueError:
return "Audio tidak dapat dikenali."
except sr.RequestError as e:
return f"Error dengan layanan pengenalan suara: {e}"
# Interface Gradio
with gr.Blocks() as demo:
with gr.Row():
gr.Markdown("## Aplikasi Input Gambar/Audio")
with gr.Row():
input_type = gr.Radio(["Gambar", "Audio"], label="Pilih Jenis Input", value="Gambar")
with gr.Row():
with gr.Column():
image_input = gr.Image(type='numpy', label="Masukkan Gambar", live=True, visible=False)
audio_input = gr.Audio(sources="microphone", type="filepath", label="Masukkan Audio", visible=False)
with gr.Column():
image_output = gr.Image(label="Hasil Gambar", visible=False)
text_output = gr.Textbox(label="Hasil Audio", visible=False)
# Fungsi untuk mengatur visibilitas berdasarkan jenis input
def update_visibility(input_type):
if input_type == "Gambar":
return (
gr.update(visible=True),
gr.update(visible=False),
gr.update(visible=True),
gr.update(visible=False),
)
elif input_type == "Audio":
return (
gr.update(visible=False),
gr.update(visible=True),
gr.update(visible=False),
gr.update(visible=True),
)
input_type.change(
update_visibility,
inputs=[input_type],
outputs=[image_input, audio_input, image_output, text_output],
)
# Menghubungkan input dengan output
image_input.change(poseImage, inputs=[image_input], outputs=[image_output])
audio_input.change(process_audio, inputs=[audio_input], outputs=[text_output])
# Menjalankan aplikasi
demo.launch()
|