Update app.py

app.py

@@ -1,7 +1,10 @@
+# imports
 import gradio as gr
 from huggingface_hub import InferenceClient
 import re
 import random
+import whisper
+from pydub import AudioSegment
 
 # uploading and cleaning the knowledge txt file
 def load_questions(file_path):
@@ -33,17 +36,33 @@ questions_by_type = {
         "testing", "financial", "automation", "analysis", "regression", "business", "stakeholder"])] 
 }
 
+# models
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-# setting up the users profile
+whisper_model = whisper.load_model("base")
+
+# whisper audio-to-text function
+def transcribe_audio(file_path):
+    try:
+        print(f"📂 Processing audio: {file_path}")
+        audio = AudioSegment.from_file(file_path)
+        converted_path = "converted.wav"
+        audio.export(converted_path, format="wav")
+        result = whisper_model.transcribe(converted_path, fp16=False)
+        return result["text"]
+    except Exception as e:
+        return f"❌ ERROR: {str(e)}"
+
+# setting up the users profile (step 1)
 def set_type(choice, user_profile):
     user_profile["interview_type"] = choice
     return "Great! What’s your background and what field/role are you aiming for?", user_profile
 
+# step 2
 def save_background(info, user_profile):
     user_profile["field"] = info
     return "Awesome! Type 'start' below to begin your interview.", user_profile
 
+# step 3
 def respond(message, chat_history, user_profile):
     message_lower = message.strip().lower()
 
@@ -122,6 +141,14 @@ def generate_feedback(user_profile):
         feedback.append(fb)
     return "\n".join(feedback)
 
+# handle audio input
+def handle_audio(audio_file, chat_history, user_profile):
+    transcribed = transcribe_audio(audio_file)
+    if transcribed.startswith("❌"):
+        chat_history.append(("Audio input", transcribed))
+        return chat_history
+    return respond(transcribed, chat_history, user_profile)
+
 # creating the visual elements
 with gr.Blocks() as demo:
     user_profile = gr.State({"interview_type": "", "field": "", "interview_in_progress": False})
@@ -152,9 +179,15 @@ with gr.Blocks() as demo:
     gr.Markdown("### Step 3: Start Interview")
     chatbot = gr.Chatbot(label="Interview Bot")
     msg = gr.Textbox(label="Your message")
-    send_btn = gr.Button("Send")
+    audio_input = gr.Audio(type="filepath", label="🎙️ Upload or Record your answer")
+
+    send_btn = gr.Button("Send Text")
+    audio_btn = gr.Button("Send Audio")
+
 
     send_btn.click(respond, inputs=[msg, chat_history, user_profile], outputs=[chatbot], queue=False)
     send_btn.click(lambda: "", None, msg, queue=False)
+    audio_btn.click(handle_audio, inputs=[audio_input, chat_history, user_profile], outputs=[chatbot], queue=False)
+
 
 demo.launch()