Enhance audio agent

audio_tools.py

@@ -16,7 +16,7 @@ class TranscribeAudioTool(Tool):
     output_type = "string"
 
     def setup(self):
-        self.model = InferenceClient(model="openai/whisper-large-v3", token=os.getenv("HUGGINGFACE_API_KEY"))
+        self.model = InferenceClient(model="openai/whisper-large-v3", provider="hf-inference", token=os.getenv("HUGGINGFACE_API_KEY"))
 
     def forward(self, audio: str) -> str:
         audio_data = base64.b64decode(audio)

mini_agents.py

@@ -41,7 +41,7 @@ audio_agent = CodeAgent(
     tools=[transcribe_audio_tool, audio_to_base64, noise_reduction, audio_segmentation, speaker_diarization],
     max_steps=6,
     # prompt_templates=PROMPT_TEMPLATE["audio_agent"],
-    additional_authorized_imports=["pytube", "pytube3", "youtube_dl", "pydub", "pyAudioAnalysis", "base64", "io", "sklearn", "scipy", "numpy", "pandas", "json", "os", "logging", "yaml", "pyplot", "matplotlib", 'hmmlearn', 'pickle'],
+    additional_authorized_imports=["wave", "speech_recognition", "pytube", "pytube3", "youtube_dl", "pydub", "pyAudioAnalysis", "base64", "io", "sklearn", "scipy", "numpy", "pandas", "json", "os", "logging", "yaml", "pyplot", "matplotlib", 'hmmlearn', 'pickle'],
     name="audio_agent",
     description="This agent is responsible for rocessing audio, transcribing audio and extracting text from it. It cannot process videos."
 )