Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,3 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
def main():
|
2 |
st.title("Visual Question Answering & Text-to-Audio App")
|
3 |
|
@@ -23,4 +36,9 @@ def main():
|
|
23 |
|
24 |
# 添加一个按钮,让用户选择是否播放音频
|
25 |
if st.button('Play Answer Audio'):
|
26 |
-
st.audio(audio_data, format="audio/ogg")
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
|
3 |
+
os.system('pip install -r requirements.txt')
|
4 |
+
from PIL import Image
|
5 |
+
import io
|
6 |
+
import streamlit as st
|
7 |
+
from transformers import pipeline
|
8 |
+
|
9 |
+
# 初始化视觉问题回答和文本到语音的管道
|
10 |
+
# 这里需要替换为你自己的模型,如果使用默认模型则可以省略 model 参数
|
11 |
+
vqa_pipeline = pipeline("visual-question-answering")
|
12 |
+
tts_pipeline = pipeline("text-to-speech")
|
13 |
+
|
14 |
def main():
|
15 |
st.title("Visual Question Answering & Text-to-Audio App")
|
16 |
|
|
|
36 |
|
37 |
# 添加一个按钮,让用户选择是否播放音频
|
38 |
if st.button('Play Answer Audio'):
|
39 |
+
st.audio(audio_data, format="audio/ogg")
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
if __name__ == "__main__":
|
44 |
+
main()
|