File size: 2,256 Bytes
d7ef93f d1b5c08 3c37a29 d1b5c08 d7ef93f d1b5c08 3c37a29 d1b5c08 3c37a29 d1b5c08 3c37a29 d1b5c08 3c37a29 d1b5c08 3c37a29 d1b5c08 3c37a29 d1b5c08 3c37a29 d1b5c08 3c37a29 d1b5c08 3c37a29 d1b5c08 6f34f52 |
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 |
from dotenv import find_dotenv, load_dotenv
from transformers import pipeline
from transformers import AutoProcessor, AutoModel
from langchain import PromptTemplate, LLMChain
from langchain.llms import GooglePalm
import scipy
import streamlit as st
load_dotenv(find_dotenv())
# img2text
def img_2_text(url):
image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
text = image_to_text(url)[0]["generated_text"]
return text
# llm
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']
)
llm = GooglePalm(temperature=0.7)
story_llm = LLMChain(llm=llm, prompt=prompt, verbose=True)
story = story_llm.predict(scenario=scenario)
return story
#
# text-to-speech
def text_to_speech(text):
processor = AutoProcessor.from_pretrained("suno/bark-small")
model = AutoModel.from_pretrained("suno/bark-small")
inputs = processor(
text=[text],
return_tensors="pt",
)
speech_values = model.generate(**inputs, do_sample=True)
sampling_rate = model.generation_config.sample_rate
scipy.io.wavfile.write("audio.wav", rate=sampling_rate, data=speech_values.cpu().numpy().squeeze())
def main():
st.set_page_config(page_title="img 2 audio story")
st.header("turn image to audio story")
uploaded_file = st.file_uploader("Choose an image ... ", type="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)
text = img_2_text(uploaded_file.name)
story = generate_story(text)
text_to_speech(story)
with st.expander("text"):
st.write(text)
with st.expander("story"):
st.write(story)
st.audio("audio.wav")
main()
|