File size: 2,403 Bytes
4ae2990 |
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 |
from dotenv import find_dotenv, load_dotenv
from transformers import pipeline
from langchain import PromptTemplate, LLMChain, OpenAI
import requests
import os
import streamlit as st
load_dotenv(find_dotenv())
HF_API_KEY=os.getenv("HF_API_KEY")
# img2text
def img2text(url):
image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
text = image_to_text_model(url)[0]["generated_text"]
print(text)
return text
# Describe it using LLM
def generate_description(caption):
template = """
You are a story teller;
You can generate a short story based on a simple narrative, the story should be no more than 30 words;
CONTEXT: {caption}
STORY;
"""
prompt = PromptTemplate(template=template, input_variables=["caption"])
desc_llm = LLMChain(llm=OpenAI(model_name="gpt-4", temperature=1), prompt=prompt, verbose=True)
description = desc_llm.predict(caption=caption).replace('"', '')
print(description)
return description
# text to speech
def text2speech(message):
API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
headers = {"Authorization": f"Bearer {HF_API_KEY}"}
payload = {
"inputs": message
}
response = requests.post(API_URL, headers=headers, json=payload)
with open('audio.flac', 'wb') as file:
file.write(response.content)
def main():
st.set_page_config(page_title="image-to-caption-to-summary", page_icon="😊")
st.header("Image to caption to summary")
uploaded_file = st.file_uploader("Choose an image", type=['png', 'jpg'])
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)
st.text('Processing img2text...')
caption = img2text(uploaded_file.name)
with st.expander("caption"):
st.write(caption)
st.text('Generating description of given image...')
description = generate_description(caption)
with st.expander("Description"):
st.write(story)
st.text('Processing text2speech...')
text2speech(story)
st.audio("audio.flac")
if __name__ == '__main__':
main() |