Update app.py

app.py

@@ -4,6 +4,8 @@ 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")
@@ -50,6 +52,21 @@ def generate_question(user_input, resume_embeddings, job_desc_embedding):
     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):
@@ -61,13 +78,13 @@ class MockInterview:
         self.resume_embeddings = process_resume(resume)
         self.job_desc_embedding = process_job_description(job_desc)
         self.interview_active = True
-        return "Resume and job description processed. Interview is ready to begin."
+        return "Resume and job description processed. Interview is starting."
 
-    def conduct_interview(self, audio):
+    def conduct_interview(self, audio_data):
         if not self.interview_active:
             return "Please upload your resume and job description first.", ""
 
-        transcription = stt_model(audio)["text"]  # Transcribe audio
+        transcription = stt_model(audio_data)["text"]  # Transcribe audio
         question = generate_question(transcription, self.resume_embeddings, self.job_desc_embedding)
         return transcription, question
 
@@ -80,11 +97,16 @@ mock_interview = MockInterview()
 def upload_inputs(resume, job_desc):
     return mock_interview.upload_inputs(resume, job_desc)
 
-def conduct_interview(audio):
-    return mock_interview.conduct_interview(audio)
+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 end_interview():
-    return mock_interview.end_interview()
+    record_audio(process_audio)
 
 interface = gr.Blocks()
 with interface:
@@ -94,20 +116,15 @@ Upload your resume and job description, then engage in a realistic interview sim
     with gr.Row():
         resume_input = gr.File(label="Upload Resume (PDF)")
         job_desc_input = gr.Textbox(label="Paste Job Description")
-        upload_button = gr.Button("Upload")
-
-    with gr.Row():
-        audio_input = gr.Audio(type="filepath", label="Speak Your Answer")
-        submit_button = gr.Button("Submit Response")
-        end_button = gr.Button("End Interview")
+        upload_button = gr.Button("Upload and Start Interview")
 
     with gr.Row():
         transcription_output = gr.Textbox(label="Transcription")
         question_output = gr.Textbox(label="Question")
+        end_button = gr.Button("End Interview")
 
     upload_button.click(upload_inputs, inputs=[resume_input, job_desc_input], outputs=[transcription_output])
-    submit_button.click(conduct_interview, inputs=[audio_input], outputs=[transcription_output, question_output])
-    end_button.click(end_interview, outputs=[transcription_output])
+    end_button.click(mock_interview.end_interview, outputs=[transcription_output])
 
 if __name__ == "__main__":
     interface.launch()