Spaces:
Sleeping
Sleeping
File size: 1,276 Bytes
8533608 9322a5c 8987036 9322a5c 8533608 c3c7832 8533608 c3c7832 8533608 c3c7832 8533608 c3c7832 |
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 |
# import part
import streamlit as st
from transformers import pipeline
# function part
# img2text
def img2text(url):
image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
text = image_to_text_model(url)[0]["generated_text"]
return text
# text2story
def text2story(text):
pipe = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
story_text = pipe(text)[0]['generated_text']
return story_text
# text2audio
def text2audio(story_text):
pipe = pipeline("text-to-audio", model="Matthijs/mms-tts-eng")
audio_data = pipe(story_text)
return audio_data
def main():
st.set_page_config(page_title="Your Image to Audio Story", page_icon="🦜")
st.header("Turn Your Image to Audio Story")
uploaded_file = st.file_uploader("Select an Image...")
if uploaded_file is not None:
print(uploaded_file)
bytes_data = uploaded_file.getvalue()
with open(uploaded_file.name, "wb") as file:
file.write(bytes_data)
st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)
#Stage 1: Image to Text
st.text('Processing img2text...')
scenario = img2text(uploaded_file.name)
st.write(scenario) |