File size: 1,928 Bytes
221ba92
 
 
 
fc48446
 
 
 
dadddbe
 
 
fc48446
221ba92
fc48446
dadddbe
 
 
fc48446
 
 
dadddbe
 
 
 
 
 
fc48446
 
 
 
 
 
 
dadddbe
221ba92
dadddbe
221ba92
dadddbe
 
df4ad39
cdac439
fc48446
dadddbe
 
fc48446
cdac439
dadddbe
 
 
fc48446
cdac439
dadddbe
 
df4ad39
dadddbe
 
 
 
 
 
 
 
 
cdac439
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
import streamlit as st
from transformers import pipeline
from gtts import gTTS
import os

# 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):
    story_generator = pipeline("text-generation", model="agentica-org/DeepScaleR-1.5B-Preview")
    story = story_generator(text, max_length=200, num_return_sequences=1)[0]['generated_text']
    return story

# text2audio
def text2audio(story_text):
    # 创建 gTTS 对象
    tts = gTTS(text=story_text, lang='en')
    # 保存音频文件
    audio_file = "story_audio.wav"
    tts.save(audio_file)
    return audio_file

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)

    # Stage 2: Text to Story
    st.text('Generating a story...')
    story = text2story(scenario)
    st.write(story)

    # Stage 3: Story to Audio data
    st.text('Generating audio data...')
    audio_file = text2audio(story)

    # Play button
    if st.button("Play Audio"):
        with open(audio_file, "rb") as audio:
            audio_bytes = audio.read()
        st.audio(audio_bytes,
                 format="audio/wav",
                 start_time=0)
    # 删除临时音频文件
    if os.path.exists(audio_file):
        os.remove(audio_file)