Update app.py

app.py

@@ -10,11 +10,11 @@ import PyPDF2
 stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-tiny")
 embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
 
-gpt_model_name = "google/flan-t5-base"
+gpt_model_name = "google/flan-t5-small"  # Switched to a smaller model for faster loading
 gpt_tokenizer = AutoTokenizer.from_pretrained(gpt_model_name)
 gpt_model = AutoModelForSeq2SeqLM.from_pretrained(gpt_model_name)
 
-tts_model = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=False)
+tts_model = TTS(model_name="tts_models/en/ljspeech/tacotron2", progress_bar=False, gpu=False)  # Using a lighter TTS model
 
 # Parse PDF and create resume content
 def parse_resume(pdf):
@@ -100,17 +100,17 @@ def finalize_interview():
 interface = gr.Blocks()
 
 with interface:
-    gr.Markdown("### Mock Interview AI\nUpload your resume and job description, and engage in a realistic audio-based mock interview simulation.")
+    gr.Markdown("### Mock Interview AI\nUpload your resume and job description, then press Submit to start the interview.")
 
     resume_input = gr.File(label="Upload Resume (PDF)")
     job_desc_input = gr.Textbox(label="Paste Job Description")
+    submit_button = gr.Button("Submit")
     audio_input = gr.Audio(type="filepath", label="Your Response")
     question_audio_output = gr.Audio(label="Question Audio")
     transcription_output = gr.Textbox(label="Transcription")
 
-    resume_input.change(start_interview, inputs=[resume_input, job_desc_input], outputs=[question_audio_output])
+    submit_button.click(start_interview, inputs=[resume_input, job_desc_input], outputs=[question_audio_output])
     audio_input.change(process_response, inputs=[audio_input], outputs=[transcription_output, question_audio_output])
-    question_audio_output.change(finalize_interview, outputs=[question_audio_output])
 
 if __name__ == "__main__":
     interface.launch()