File size: 1,513 Bytes
e585f50 f42c65b 536a548 f42c65b e585f50 536a548 c545edf 536a548 f42c65b 536a548 e585f50 536a548 e585f50 536a548 e585f50 f42c65b e585f50 f42c65b e585f50 f42c65b |
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 |
import os
from PIL import Image, ImageDraw, ImageFont
import gradio as gr
from helper import load_image_from_url, render_results_in_image
from helper import summarize_predictions_natural_language
from transformers import pipeline
from transformers.utils import logging
logging.set_verbosity_error()
from helper import ignore_warnings
ignore_warnings()
od_pipe = pipeline("object-detection", "facebook/detr-resnet-50")
tts_pipe = pipeline("text-to-speech",
model="kakao-enterprise/vits-ljs")
def get_pipeline_prediction(pil_image):
pipeline_output = od_pipe(pil_image)
processed_image = render_results_in_image(pil_image,
pipeline_output)
text = summarize_predictions_natural_language(pipeline_output)
print(text)
narrated_text = tts_pipe(text)
#print (narrated_text)
print(narrated_text["audio"][0])
print (narrated_text["sampling_rate"])
return processed_image, (narrated_text["sampling_rate"], narrated_text["audio"][0] )
#return processed_image
demo = gr.Interface(
fn=get_pipeline_prediction,
inputs=gr.Image(label="Input image",
type="pil"),
outputs=[gr.Image(label="Output image with predicted instances",
type="pil"), gr.Audio(label="Narration", type="numpy", autoplay=True)]
#outputs=gr.Image(label="Output image with predicted instances",
# type="pil")
)
demo.launch(server_name="0.0.0.0", server_port=7860)
|