Update app.py

app.py

@@ -90,7 +90,7 @@ HF_TOKEN = os.environ.get("HF_TOKEN")
 # will use api to restart space on a unrecoverable error
 api = HfApi(token=HF_TOKEN)
 
-repo_id = "coqui/voice-chat-with-zephyr"
+repo_id = "coqui/voice-chat-with-mistral"
 
 
 default_system_message = f"""
@@ -208,41 +208,13 @@ def format_prompt_zephyr(message, history, system_message=system_message):
     print(prompt)
     return prompt
 
-def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
-    top_p = float(top_p)
-
-    generate_kwargs = dict(
-        temperature=temperature,
-        max_tokens=max_new_tokens,
-        max_new_tokens=max_new_tokens,
-        top_p=top_p,
-        stop=LLM_STOP_WORDS
-    )
-    formatted_prompt = format_prompt(prompt, history)
-
-    del generate_kwargs["max_tokens"]
-    del generate_kwargs["stop"]
-    
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
-
-    for response in stream:
-        output += response.token.text
-        yield output
-    return output
-    
 def generate_local(
     prompt,    
     history,
     llm_model="zephyr",
     system_message=None,
-    temperature=0.8,
-    max_tokens=256,
+    temperature=0.85,
+    max_tokens=128,
     top_p=0.95,
     stop = LLM_STOP_WORDS
 ):
@@ -296,7 +268,7 @@ def generate_local(
                 return
                 
             
-            output += response["choices"][0]["text"].replace("<|assistant|>","").replace("<|user|>","")
+            output += character.replace("<|assistant|>","").replace("<|user|>","")
             yield output
 
     except Exception as e: