Update app.py

app.py

@@ -1,16 +1,35 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import whisper
+from pydub import AudioSegment
 
+# Load models
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+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)}"
+
+# ---------- 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):
     if not user_profile.get("interview_type") or not user_profile.get("field"):
         bot_msg = "Please finish steps 1 and 2 before starting the interview."
@@ -30,13 +49,22 @@ def respond(message, chat_history, user_profile):
     chat_history.append((message, bot_msg))
     return chat_history
 
+# ---------- 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)
+
+# ---------- Gradio UI ----------
 with gr.Blocks() as demo:
     user_profile = gr.State({"interview_type": "", "field": ""})
     chat_history = gr.State([])
 
     gr.Markdown("# 🎤 Welcome to Intervu")
 
-    # Step 1
+    # Step 1: Choose Interview Type
     gr.Markdown("### Step 1: Choose Interview Type")
     with gr.Row():
         with gr.Column():
@@ -49,7 +77,7 @@ with gr.Blocks() as demo:
     btn2.click(set_type, inputs=[gr.Textbox(value="Technical", visible=False), user_profile], outputs=[type_output, user_profile])
     btn3.click(set_type, inputs=[gr.Textbox(value="College", visible=False), user_profile], outputs=[type_output, user_profile])
 
-    # Step 2
+    # Step 2: Enter Background
     gr.Markdown("### Step 2: Enter Your Background")
     background = gr.Textbox(label="Your background and field/goal")
     background_btn = gr.Button("Submit")
@@ -57,13 +85,22 @@ with gr.Blocks() as demo:
 
     background_btn.click(save_background, inputs=[background, user_profile], outputs=[background_output, user_profile])
 
-    # Step 3
+    # Step 3: Interview Chat
     gr.Markdown("### Step 3: Start Interview")
     chatbot = gr.Chatbot(label="Interview Bot")
-    msg = gr.Textbox(label="Your message")
-    send_btn = gr.Button("Send")
+
+    with gr.Row():
+        msg = gr.Textbox(label="Your message")
+        audio_input = gr.Audio(source="microphone", type="filepath", label="🎙️ Or record your answer")
+
+    with gr.Row():
+        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)
+
+# ---------- Launch App ----------
 demo.launch()