Update app.py

app.py

@@ -1,12 +1,9 @@
-from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
+from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
 import datetime
 import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
-import os
-import scipy.io.wavfile
-from transformers import BarkModel, BarkTokenizer
 
 from Gradio_UI import GradioUI
 
@@ -16,39 +13,6 @@ print(transformers.__version__)
 tokenizer = BarkTokenizer.from_pretrained("suno/bark-small")
 model = BarkModel.from_pretrained("suno/bark-small")
 
-
-# Define the text-to-speech tool
-@tool
-def text_to_speech(text: str) -> bytes:
-    """
-    Converts text to speech using the Bark model.
-
-    Args:
-        text: The text to be converted to speech.
-
-    Returns:
-        bytes: The audio data in WAV format.
-    """
-    try:
-        inputs = tokenizer(text, return_tensors="pt")
-        audio_array = model.generate(**inputs)
-        # Convert the generated audio array to a NumPy array
-        audio_array = audio_array.cpu().numpy()
-
-        # Save the audio array as a WAV file
-        rate = 16000 # Bark model sample rate
-        filename = "output.wav"
-        scipy.io.wavfile.write(filename, rate, audio_array)
-
-        # Read the WAV file and convert it to bytes
-        with open(filename, "rb") as f:
-            audio_bytes = f.read()
-
-        return audio_bytes
-
-    except Exception as e:
-        return f"Error converting text to speech: {str(e)}".encode('utf-8')
-
 # Define the get current time in timezone tool
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
@@ -87,7 +51,7 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer, image_generation_tool, text_to_speech], ## add your tools here (don't remove final answer)
+    tools=[final_answer, image_generation_tool, get_current_time_in_timezone], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,