Update app.py

app.py

@@ -1,8 +1,9 @@
+import os
+os.environ["TRANSFORMERS_NO_FLASH_ATTN"] = "1"
+
 import torch
 import gradio as gr
 from transformers import AutoModel, AutoTokenizer
-import warnings
-warnings.filterwarnings("ignore")
 
 MODEL_NAME = "openbmb/MiniCPM-o-2_6"
 
@@ -13,7 +14,7 @@ model = AutoModel.from_pretrained(
     trust_remote_code=True,
     torch_dtype=torch.float32,
     low_cpu_mem_usage=True,
-    attn_implementation="eager"
+    attn_implementation="eager"   # 🔥 IMPORTANT FIX
 )
 
 model = model.eval()
@@ -23,48 +24,47 @@ tokenizer = AutoTokenizer.from_pretrained(
     trust_remote_code=True
 )
 
-# TTS init (safe)
+# Init TTS safely
 try:
     model.init_tts()
     print("TTS ready")
 except Exception as e:
-    print("TTS warning:", e)
+    print("TTS not available:", e)
 
-def chat_with_voice(text):
+def chat(text):
 
     msgs = [
         {"role": "user", "content": [text]}
     ]
 
-    output_path = "voice_output.wav"
+    audio_path = "output.wav"
+
+    try:
+        result = model.chat(
+            msgs=msgs,
+            tokenizer=tokenizer,
+            generate_audio=True,
+            output_audio_path=audio_path,
+            max_new_tokens=200,
+            temperature=0.3
+        )
 
-    result = model.chat(
-        msgs=msgs,
-        tokenizer=tokenizer,
-        generate_audio=True,
-        output_audio_path=output_path,
-        temperature=0.3,
-        max_new_tokens=200
-    )
+        reply = result if isinstance(result, str) else text
 
-    # return text + audio player
-    reply_text = result if isinstance(result, str) else "Response generated"
+        return reply, audio_path
 
-    return reply_text, output_path
+    except Exception as e:
+        return str(e), None
 
 
-# UI
 demo = gr.Interface(
-    fn=chat_with_voice,
-    inputs=gr.Textbox(label="Enter your message"),
+    fn=chat,
+    inputs=gr.Textbox(label="Type message"),
     outputs=[
-        gr.Textbox(label="AI Reply"),
-        gr.Audio(label="Voice Output (Play)")
+        gr.Textbox(label="Reply"),
+        gr.Audio(label="Voice Output")
     ],
-    title="MiniCPM Voice Assistant (CPU)"
+    title="MiniCPM-o Voice Chatbot (CPU Stable)"
 )
 
-demo.launch(
-    server_name="0.0.0.0",
-    server_port=7860
-)
+demo.launch(server_name="0.0.0.0", server_port=7860)