Update app.py

app.py

@@ -4,8 +4,6 @@ from transformers import pipeline
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 import PyPDF2
-import sounddevice as sd
-import queue
 
 # Load local models for inference
 stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-base")
@@ -35,38 +33,17 @@ def process_resume(pdf):
     }
     return resume_embeddings
 
-# Generate a conversation response
-def generate_conversation_response(user_input, job_desc_embedding):
-    prompt = f"The user said: {user_input}. Respond appropriately as a professional hiring manager. Focus on how the response relates to the job description."
-    response = conversation_model(prompt, max_length=100, num_return_sequences=1)
-    return response[0]["generated_text"]
-
 # Generate question from user response
-def generate_question(user_input, resume_embeddings, job_desc_embedding):
+def generate_question(user_input, resume_embeddings):
     """Find the most relevant section in the resume and generate a question."""
     user_embedding = embedding_model.encode(user_input)
     similarities = {
-        section: cosine_similarity([user_embedding], [embedding])[0][0] 
+        section: cosine_similarity([user_embedding], [embedding])[0][0]
         for section, embedding in resume_embeddings.items()
     }
     most_relevant_section = max(similarities, key=similarities.get)
     return f"Based on your experience in {most_relevant_section}, can you elaborate more?"
 
-# Real-time audio recording and processing
-def record_audio(callback):
-    """Record audio and process it in real-time."""
-    q = queue.Queue()
-
-    def audio_callback(indata, frames, time, status):
-        if status:
-            print(status)
-        q.put(indata.copy())
-
-    with sd.InputStream(samplerate=16000, channels=1, callback=audio_callback):
-        while True:
-            audio_data = q.get()
-            callback(audio_data)
-
 # Gradio interface
 class MockInterview:
     def __init__(self):
@@ -80,12 +57,12 @@ class MockInterview:
         self.interview_active = True
         return "Resume and job description processed. Interview is starting."
 
-    def conduct_interview(self, audio_data):
+    def conduct_interview(self, audio_file):
         if not self.interview_active:
             return "Please upload your resume and job description first.", ""
 
-        transcription = stt_model(audio_data)["text"]  # Transcribe audio
-        question = generate_question(transcription, self.resume_embeddings, self.job_desc_embedding)
+        transcription = stt_model(audio_file)["text"]  # Transcribe audio
+        question = generate_question(transcription, self.resume_embeddings)
         return transcription, question
 
     def end_interview(self):
@@ -97,16 +74,11 @@ mock_interview = MockInterview()
 def upload_inputs(resume, job_desc):
     return mock_interview.upload_inputs(resume, job_desc)
 
-def start_interview(audio_data_callback):
-    """Start the interview automatically, processing audio in real-time."""
-    if not mock_interview.interview_active:
-        return "Please upload your resume and job description first."
-
-    def process_audio(audio_data):
-        transcription, question = mock_interview.conduct_interview(audio_data)
-        audio_data_callback(transcription, question)
+def conduct_interview(audio_file):
+    return mock_interview.conduct_interview(audio_file)
 
-    record_audio(process_audio)
+def end_interview():
+    return mock_interview.end_interview()
 
 interface = gr.Blocks()
 with interface:
@@ -119,12 +91,15 @@ Upload your resume and job description, then engage in a realistic interview sim
         upload_button = gr.Button("Upload and Start Interview")
 
     with gr.Row():
+        audio_input = gr.Audio(type="filepath", label="Respond with Your Answer")
         transcription_output = gr.Textbox(label="Transcription")
         question_output = gr.Textbox(label="Question")
+        submit_button = gr.Button("Submit Response")
         end_button = gr.Button("End Interview")
 
     upload_button.click(upload_inputs, inputs=[resume_input, job_desc_input], outputs=[transcription_output])
-    end_button.click(mock_interview.end_interview, outputs=[transcription_output])
+    submit_button.click(conduct_interview, inputs=[audio_input], outputs=[transcription_output, question_output])
+    end_button.click(end_interview, outputs=[transcription_output])
 
 if __name__ == "__main__":
     interface.launch()