Update web_demo.py

web_demo.py

@@ -114,18 +114,27 @@ if __name__ == "__main__":
         if "<|system|>" not in inputs:
             inputs += f"<|system|>\n{system_prompt}"
         inputs += f"<|user|>\n{user_input}<|assistant|>streaming_transcription\n"
-
+        
+        global use_local_interface , worker  
         with torch.no_grad():
-            response = requests.post(
-                "http://localhost:10000/generate_stream",
-                data=json.dumps({
-                    "prompt": inputs,
-                    "temperature": temperature,
-                    "top_p": top_p,
-                    "max_new_tokens": max_new_token,
-                }),
-                stream=True
-            )
+            if  use_local_interface :
+                params = {  "prompt": inputs,
+                            "temperature": temperature,
+                            "top_p": top_p,
+                            "max_new_tokens": max_new_token, } 
+                response = worker.generate_stream( params ) 
+                
+            else :
+                response = requests.post(
+                    "http://localhost:10000/generate_stream",
+                    data=json.dumps({
+                        "prompt": inputs,
+                        "temperature": temperature,
+                        "top_p": top_p,
+                        "max_new_tokens": max_new_token,
+                    }),
+                    stream=True
+                )
             text_tokens, audio_tokens = [], []
             audio_offset = glm_tokenizer.convert_tokens_to_ids('<|audio_0|>')
             end_token_id = glm_tokenizer.convert_tokens_to_ids('<|user|>')