Spaces:
Runtime error
Runtime error
File size: 2,697 Bytes
aec954b f1cff78 aec954b f1cff78 aec954b e829c4e aec954b |
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 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
from transformers import pipeline
from langchain import PromptTemplate, LLMChain
from langchain_community.chat_models import ChatGooglePalm
import requests
import os
import streamlit as st
os.environ["GOOGLE_API_KEY"] = "AIzaSyD29fEos3V6S2L-AGSQgNu03GqZEIgJads"
os.environ ["HUGGINGFACEHUB_API_TOKEN"] = "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"
llm = ChatGooglePalm(temperature = 0.5)
#image to text
def image2text(url):
image_to_text = pipeline("image-to-text", model = "Salesforce/blip-image-captioning-large")
text = image_to_text(
url)[0]['generated_text']
print(text)
return(text)
#story teller
def generate_story(scenario):
template = """"
You are a story teller;
you can generate a creative fun story based on a sample narrative, the story should not be more than 100 words;
CONTEXT: {scenario}
STORY:
"""
prompt = PromptTemplate(template = template,
input_variables = ['scenario']
)
story_llm = LLMChain(llm=llm, prompt = prompt, verbose = True)
story = story_llm.predict(scenario = scenario)
print(story)
return(story)
#text to speech
def text2speech(message):
API_URL = "https://api-inference.huggingface.co/models/espnet/fastspeech2_conformer"
headers = {"Authorization": "Bearer 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"}
payloads = {
"inputs":message
}
response = requests.post(API_URL, headers = headers, json= payloads)
with open("audio.flac", "wb") as file:
file.write(response.content)
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)
scenario = image2text(uploaded_file.name)
st.subheader("Image Details:")
st.write(scenario)
story = generate_story(scenario)
st.subheader("Story:")
st.write(story)
text2speech(story)
st.subheader("Generated Audio:")
st.audio("audio.flac", format="audio/flac")
# Add a download link for the audio
st.subheader("Download Audio:")
with open("audio.flac", "rb") as audio_file:
st.download_button(label="Download Audio", data=audio_file, file_name="generated_audio.flac", mime="audio/flac")
if __name__ == "__main__":
main()
|