Update app.py

app.py

@@ -5,58 +5,91 @@ import pandas as pd # Still useful for example dataframes if needed for report t
 
 # --- TTS Model Functions (CPU Friendly) ---
 
-def synthesize_espeak(text, lang="en-us"):
+def synthesize_espeak(text: str, lang: str = "en-us") -> str | None:
     """
     Synthesizes speech using espeak-ng.
     Requires espeak-ng to be installed in the Space environment (via Dockerfile).
     """
     output_file = "espeak_output.wav"
+    
+    # Clean up previous output file if it exists
+    if os.path.exists(output_file):
+        os.remove(output_file)
+
     try:
-        # -v: voice, -w: output to WAV file, --stdout: write to stdout (less common for WAV)
-        # Using a temporary file for output
+        # Command to run espeak-ng. --stdout outputs to stdout, which we capture.
         command = ["espeak-ng", f"-v{lang}", "--stdout", text]
         
-        # Capture stdout as bytes and save to file
-        process = subprocess.run(command, capture_output=True, check=True)
+        # Execute the command. Added timeout to prevent infinite hangs.
+        process = subprocess.run(command, capture_output=True, check=True, timeout=10)
+        
+        # Check if espeak-ng actually produced audio output
+        if not process.stdout:
+            gr.Warning("eSpeak-ng produced no audio output for the given text. Try different text.")
+            print(f"eSpeak-ng produced no output for text: '{text}'")
+            return None # Return None to clear the audio component
+
+        # Write the captured stdout (audio data) to a WAV file
         with open(output_file, "wb") as f:
             f.write(process.stdout)
             
         print(f"eSpeak-ng synthesis successful: {output_file}")
-        return output_file
+        return output_file # Return the path to the generated audio file
+    
     except FileNotFoundError:
-        error_msg = "Error: espeak-ng not found. Please ensure it's installed in your Space's Dockerfile."
+        error_msg = "Error: espeak-ng not found. Please ensure it's installed in your Space's Dockerfile and the Space is rebuilt."
         print(error_msg)
-        return None # Return None or raise an error for Gradio to handle
+        gr.Error(error_msg) # Show a persistent error message in Gradio
+        return None 
     except subprocess.CalledProcessError as e:
-        error_msg = f"Error during espeak-ng synthesis: {e.stderr.decode()}"
+        error_msg = f"Error during espeak-ng synthesis. Command exited with code {e.returncode}. Stderr: {e.stderr.decode()}"
+        print(error_msg)
+        gr.Error(error_msg)
+        return None
+    except subprocess.TimeoutExpired:
+        error_msg = "eSpeak-ng command timed out. The text might be too long or complex."
         print(error_msg)
+        gr.Warning(error_msg)
         return None
     except Exception as e:
         error_msg = f"An unexpected error occurred during espeak-ng synthesis: {e}"
         print(error_msg)
+        gr.Error(error_msg)
         return None
 
-def synthesize_api_tts(text):
+def synthesize_api_tts(text: str) -> str | None:
     """
     Placeholder for an API-based Text-to-Speech service (e.g., Azure TTS, Google TTS).
     In a real application, you would make an HTTP request to the API here.
     For this demo, it returns a placeholder audio file.
     """
     print(f"Simulating API TTS for: '{text}'")
-    # Replace this with actual API call using 'requests' library
-    # Example:
+    
+    # --- IMPORTANT: Replace this with your actual API call ---
+    # Example using requests (requires 'requests' in requirements.txt):
     # import requests
-    # url = "YOUR_TTS_API_ENDPOINT"
-    # headers = {"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"}
-    # data = {"text": text, "voice": "some_api_voice"}
-    # response = requests.post(url, json=data)
-    # if response.status_code == 200:
-    #     with open("api_output.mp3", "wb") as f:
+    # try:
+    #     url = "YOUR_TTS_API_ENDPOINT" # Replace with your actual API endpoint
+    #     headers = {"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"} # Replace with your auth
+    #     data = {"text": text, "voice": "some_api_voice"} # Adjust payload as per API documentation
+    #     response = requests.post(url, json=data, timeout=15)
+    #     response.raise_for_status() # Raise an HTTPError for bad responses (4xx or 5xx)
+    #     
+    #     api_output_file = "api_output.mp3" # Or .wav, depending on API
+    #     with open(api_output_file, "wb") as f:
     #         f.write(response.content)
-    #     return "api_output.mp3"
-    # else:
-    #     print(f"API Error: {response.status_code} - {response.text}")
-    #     return None # Return None for error
+    #     return api_output_file
+    # except requests.exceptions.RequestException as e:
+    #     error_msg = f"API TTS request failed: {e}"
+    #     print(error_msg)
+    #     gr.Error(error_msg)
+    #     return None
+    # except Exception as e:
+    #     error_msg = f"An unexpected error occurred with API TTS: {e}"
+    #     print(error_msg)
+    #     gr.Error(error_msg)
+    #     return None
+    # --------------------------------------------------------
     
     # Placeholder: Return a generic audio for demonstration
     # In a real scenario, you'd fetch an actual audio file from the API.
@@ -138,7 +171,7 @@ with gr.Blocks(css="""
 
                 1.  **eSpeak-ng:**
                     * **类型与背景：** eSpeak-ng 是一个开源的语音合成器，基于**音素拼接**技术。它通过将预先录制或合成的音素拼接起来生成语音。其核心优势在于极低的资源消耗和极快的合成速度，可以在没有 GPU 的情况下高效运行。它支持多种语言，但声音通常听起来比较机械和“机器人化”。
-                    * **用途对比：** 适用于对语音质量要求不高，但对资源限制严格、需要快速生成语音的场景，例如嵌入式设备、辅助技术或批量文本预览。
+                    * **用途对比：：** 适用于对语音质量要求不高，但对资源限制严格、需要快速生成语音的场景，例如嵌入式设备、辅助技术或批量文本预览。
                     * **异同点分析：** * **异：** 采用传统拼接技术，非深度学习模型。
                         * **同：** 均能实现文本到语音的转换。
 
@@ -215,13 +248,13 @@ with gr.Blocks(css="""
 
                 ### 多条统一输入样例输出结果表格
 
-                | 输入文本 (中文)                       | 输入文本 (英文)                   | eSpeak-ng 输出特点                       | API TTS 示例输出特点                     |
-                | :---------------------------------- | :-------------------------------- | :------------------------------------- | :----------------------------------- |
-                | 你好，这是一个文本转音频的测试。      | Hello, this is a text-to-speech test. | 机械、音调平直，有明显的合成感。         | 流畅、自然，有起伏和韵律，接近人声。     |
-                | 请问今天天气怎么样？                  | What's the weather like today?      | 语调缺乏疑问语气，略显生硬。             | 能体现疑问语气，更自然。                 |
-                | 天气真好啊！                        | What a beautiful day!               | 无法表达情感，音量和速度变化不大。       | 能体现积极情感，语调更富表现力。         |
-                | 复杂一点的句子，比如人工智能的未来发展。 | The future development of artificial intelligence. | 容易在长句中出现不自然的停顿或节奏问题。 | 较好地处理复杂长句，保持流畅性。         |
-                | (在此处添加更多您的测试样例)           | (在此处添加更多您的测试样例)        | (描述 eSpeak-ng 的输出)                 | (描述 API TTS 示例的输出)                 |
+                | 输入文本 (中文) | 输入文本 (英文) | eSpeak-ng 输出特点 | API TTS 示例输出特点 |
+                | :--- | :--- | :--- | :--- |
+                | 你好，这是一个文本转音频的测试。 | Hello, this is a text-to-speech test. | 机械、音调平直，有明显的合成感。 | 流畅、自然，有起伏和韵律，接近人声。 |
+                | 请问今天天气怎么样？ | What's the weather like today? | 语调缺乏疑问语气，略显生硬。 | 能体现疑问语气，更自然。 |
+                | 天气真好啊！ | What a beautiful day! | 无法表达情感，音量和速度变化不大。 | 能体现积极情感，语调更富表现力。 |
+                | 复杂一点的句子，比如人工智能的未来发展。 | The future development of artificial intelligence. | 容易在长句中出现不自然的停顿或节奏问题。 | 较好地处理复杂长句，保持流畅性。 |
+                | (在此处添加更多您的测试样例) | (在此处添加更多您的测试样例) | (描述 eSpeak-ng 的输出) | (描述 API TTS 示例的输出) |
 
                 ### 雷达图或柱状图展示维度评分
 
@@ -260,4 +293,5 @@ with gr.Blocks(css="""
             )
 
 # --- Launch Gradio Demo ---
+# Using queue() is good practice for Spaces
 demo.queue().launch()