czhaobt commited on
Commit
fc48446
·
verified ·
1 Parent(s): 42250e0

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +68 -0
app.py ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from transformers import pipeline
3
+ from gtts import gTTS
4
+ import io
5
+ import os
6
+
7
+ # function part
8
+ # img2text
9
+ def img2text(url):
10
+ image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
11
+ text = image_to_text_model(url)[0]["generated_text"]
12
+ return text
13
+
14
+ # text2story
15
+ def text2story(text):
16
+ story_generator = pipeline("text-generation", model="Qwen/QwQ-32B")
17
+ story = story_generator(text, max_length=200, num_return_sequences=1)[0]["generated_text"]
18
+ return story
19
+
20
+ # text2audio
21
+ def text2audio(story_text):
22
+ # 创建 gTTS 对象
23
+ tts = gTTS(text=story_text, lang='en')
24
+ # 创建一个字节流对象用于存储音频数据
25
+ audio_file = io.BytesIO()
26
+ # 将音频数据写入字节流
27
+ tts.write_to_fp(audio_file)
28
+ # 将文件指针移到开头
29
+ audio_file.seek(0)
30
+ return audio_file
31
+
32
+ st.set_page_config(page_title="Your Image to Audio Story",
33
+ page_icon="🦜")
34
+ st.header("Turn Your Image to Audio Story")
35
+ uploaded_file = st.file_uploader("Select an Image...")
36
+
37
+ if uploaded_file is not None:
38
+ # 保存上传的文件到临时文件
39
+ temp_file_path = "temp_image.jpg"
40
+ bytes_data = uploaded_file.getvalue()
41
+ with open(temp_file_path, "wb") as file:
42
+ file.write(bytes_data)
43
+ st.image(uploaded_file, caption="Uploaded Image",
44
+ use_column_width=True)
45
+
46
+ # Stage 1: Image to Text
47
+ st.text('Processing img2text...')
48
+ scenario = img2text(temp_file_path)
49
+ st.write(scenario)
50
+
51
+ # 删除临时文件
52
+ if os.path.exists(temp_file_path):
53
+ os.remove(temp_file_path)
54
+
55
+ # Stage 2: Text to Story
56
+ st.text('Generating a story...')
57
+ story = text2story(scenario)
58
+ st.write(story)
59
+
60
+ # Stage 3: Story to Audio data
61
+ st.text('Generating audio data...')
62
+ audio_data = text2audio(story)
63
+
64
+ # Play button
65
+ if st.button("Play Audio"):
66
+ st.audio(audio_data,
67
+ format="audio/mpeg",
68
+ start_time=0)