Update app.py

app.py

@@ -1,64 +1,63 @@
+import os
+import whisper
+from gtts import gTTS
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from groq import Groq
+
+# Load the Whisper model for speech-to-text
+whisper_model = whisper.load_model("large")
+
+# Initialize Groq client for text generation
+GROQ_API_KEY = "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"
+client = Groq(api_key=GROQ_API_KEY)
+
+# Function to convert text to speech using gTTS and return the audio path
+def text_to_speech(text):
+    tts = gTTS(text)
+    response_audio_path = "response.mp3"
+    tts.save(response_audio_path)
+    return response_audio_path
+
+# Function to transcribe audio to text using Whisper
+def transcribe_audio(audio):
+    print("Transcribing audio...")
+    result = whisper_model.transcribe(audio)
+    return result["text"]
+
+# Function to get a response from the Groq API using LLaMA model
+def get_response_from_groq(input_text):
+    chat_completion = client.chat.completions.create(
+        messages=[{"role": "user", "content": input_text}],
+        model="llama3-8b-8192",
+    )
+    response = chat_completion.choices[0].message.content
+    return response
+
+# Gradio function to handle chatbot interaction
+def chatbot(audio):
+    # Step 1: Transcribe audio to text using Whisper
+    user_input = transcribe_audio(audio)
+    print(f"User said: {user_input}")
+    
+    # Step 2: Get chatbot response from Groq (LLaMA model)
+    response = get_response_from_groq(user_input)
+    print(f"Chatbot response: {response}")
+    
+    # Step 3: Convert response text to speech and return audio
+    response_audio_path = text_to_speech(response)
+    
+    # Return text response and audio file for playback
+    return response, response_audio_path
+
+# Gradio interface for the chatbot
+interface = gr.Interface(
+    fn=chatbot,
+    inputs=gr.Audio(source="microphone", type="filepath"),  # Using microphone as input
+    outputs=["text", gr.Audio(type="filepath")],  # Text and audio output
+    live=True,
+    title="Voice-Enabled Chatbot",
+    description="Speak into your microphone, and the chatbot will respond with both text and audio."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch Gradio interface
+interface.launch(share=True)