Update app.py

app.py

@@ -1,47 +1,29 @@
 import streamlit as st
 from transformers import pipeline
 from gtts import gTTS
-import io
 import os
 
 # function part
 # img2text
 def img2text(url):
-    try:
-        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
-    except Exception as e:
-        st.error(f"图像转文本出错: {e}")
-        return None
+    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):
-    try:
-        story_generator = pipeline("text-generation", model="Qwen/QwQ-32B-Preview")
-        # 生成故事文本
-        result = story_generator(text, max_length=200, num_return_sequences=1)
-        story = result[0]['generated_text']
-        return story
-    except Exception as e:
-        st.error(f"文本生成故事出错: {e}")
-        return None
+    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):
-    try:
-        # 创建 gTTS 对象，将文本转换为语音
-        tts = gTTS(text=story_text, lang='en')
-        # 创建字节流对象用于存储音频数据
-        audio_file = io.BytesIO()
-        # 将音频数据写入字节流
-        tts.write_to_fp(audio_file)
-        # 移动文件指针到开头
-        audio_file.seek(0)
-        return audio_file
-    except Exception as e:
-        st.error(f"文本转音频出错: {e}")
-        return None
+    # 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="🦜")
@@ -49,35 +31,34 @@ st.header("Turn Your Image to Audio Story")
 uploaded_file = st.file_uploader("Select an Image...")
 
 if uploaded_file is not None:
-    # 使用临时文件存储上传的图像
-    temp_file_path = "temp_image.jpg"
+    print(uploaded_file)
     bytes_data = uploaded_file.getvalue()
-    with open(temp_file_path, "wb") as file:
+    with open(uploaded_file.name, "wb") as file:
         file.write(bytes_data)
+    st.image(uploaded_file, caption="Uploaded Image",
+             use_column_width=True)
 
-    # 显示上传的图像，使用 use_container_width 避免弃用警告
-    st.image(uploaded_file, caption="Uploaded Image", use_container_width=True)
-
-    # Stage 1: Image to Text
+    #Stage 1: Image to Text
     st.text('Processing img2text...')
-    scenario = img2text(temp_file_path)
-    if scenario:
-        st.write(scenario)
+    scenario = img2text(uploaded_file.name)
+    st.write(scenario)
 
-        # Stage 2: Text to Story
-        st.text('Generating a story...')
-        story = text2story(scenario)
-        if story:
-            st.write(story)
+    #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_data = text2audio(story)
-            if audio_data:
-                # Play button
-                if st.button("Play Audio"):
-                    st.audio(audio_data, format="audio/mpeg", start_time=0)
+    #Stage 3: Story to Audio data
+    st.text('Generating audio data...')
+    audio_file = text2audio(story)
 
-    # 删除临时文件
-    if os.path.exists(temp_file_path):
-        os.remove(temp_file_path)
+    # 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)