Spaces:
Sleeping
Sleeping
File size: 1,591 Bytes
42ef26d 92615bf 42ef26d 722f574 42ef26d 50a2f63 722f574 50a2f63 722f574 c88106c 722f574 c88106c ac026ae 5ba51aa 42ef26d ac026ae 5ba51aa ac026ae 5ba51aa ac026ae 5ba51aa c714d05 42ef26d 2f90508 c714d05 2f90508 |
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 |
import gradio as gr
from transformers import pipeline
from helper import load_image_from_url, render_results_in_image
from helper import summarize_predictions_natural_language
od_pipe = pipeline("object-detection", model="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)
text = summarize_predictions_natural_language(pipeline_output)
#text = "Hello, my name is Ratha"
gen_audio = tts_pipe(text)
processed_image = render_results_in_image(pil_image,
pipeline_output)
rate= gen_audio["sampling_rate"]
return processed_image, text, (rate, gen_audio["audio"][0])
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.Textbox(label="Prediction Summary"),
gr.Audio(label="Generated Speech")]
)
demo.launch()
#text = itt_pipe(input)
#tts_pipe = pipeline("text-to-speech",
# model="kakao-enterprise/vits-ljs")
#narrated_text = tts_pipe(tts_pipe[0]['generated_text'])
#def launch(text):
# out = tts_pipe(text)
# audio = IPythonAudio(out["audio"][0],
# rate=out["sampling_rate"])
# return audio
#iface = gr.Interface(launch,
# inputs=gr.Image(type='pil'),
# outputs="text")
#iface.launch()
|