Spaces:
Sleeping
Sleeping
File size: 2,272 Bytes
4fddba4 4e17b21 4fddba4 4e17b21 4fddba4 4e17b21 4fddba4 4e17b21 4fddba4 4e17b21 4fddba4 4e17b21 4fddba4 4e17b21 4fddba4 4e17b21 |
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 |
# import part
import streamlit as st
from transformers import pipeline
from gtts import gTTS
import os
# function part
# img2text
def img2text(url):
try:
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
except Exception as e:
st.error(f"Error in image to text conversion: {e}")
return None
# text2story
def text2story(text):
try:
story_generator = pipeline("text-generation", model="gpt2")
story = story_generator(text, max_length=100, num_return_sequences=1)[0]["generated_text"]
return story
except Exception as e:
st.error(f"Error in story generation: {e}")
return None
# text2audio
def text2audio(story_text):
try:
tts = gTTS(text=story_text, lang='en')
audio_file = "story_audio.mp3"
tts.save(audio_file)
return audio_file
except Exception as e:
st.error(f"Error in text to audio conversion: {e}")
return None
# main part
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...", type=["jpg", "jpeg", "png"])
if uploaded_file is not None:
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)
if scenario:
st.write("Image Caption:", scenario)
# Stage 2: Text to Story
st.text('Generating a story...')
story = text2story(scenario)
if story:
st.write("Generated Story:", story)
# Stage 3: Story to Audio data
st.text('Generating audio data...')
audio_file = text2audio(story)
if audio_file:
# Play button
if st.button("Play Audio"):
st.audio(audio_file, format="audio/mp3")
# Clean up the audio file after playing
os.remove(audio_file) |