Update app.py

app.py

@@ -4,24 +4,15 @@ from transformers import pipeline
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 import PyPDF2
-import pyttsx3
-import time
 
 # Load local models for inference
 stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-base")
 conversation_model = pipeline("text-generation", model="facebook/blenderbot-400M-distill")
+tts_model = pipeline("text-to-speech", model="espnet/fastspeech2-en-ljspeech")
 
 # Load a pre-trained model for vector embeddings
 embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
 
-# Text-to-Speech engine setup
-tts_engine = pyttsx3.init()
-
-def speak_text(text):
-    """Speak the given text using TTS engine."""
-    tts_engine.say(text)
-    tts_engine.runAndWait()
-
 # Parse PDF and create resume content
 def parse_resume(pdf):
     """Extract text from an uploaded PDF file."""
@@ -54,6 +45,12 @@ def generate_question(user_input, resume_embeddings):
     most_relevant_section = max(similarities, key=similarities.get)
     return f"Based on your experience in {most_relevant_section}, can you elaborate more?"
 
+# Generate TTS output
+def generate_audio(text):
+    """Convert text to audio using TTS model."""
+    audio_data = tts_model(text, return_tensors=True)["waveform"]
+    return audio_data
+
 # Gradio interface
 class MockInterview:
     def __init__(self):
@@ -65,42 +62,34 @@ 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. Starting the interview."
-
-    def start_interview(self):
-        if not self.interview_active:
-            return "Please upload your resume and job description first."
         question = "Tell me about yourself."
-        speak_text(question)
-        return question
+        audio_output = generate_audio(question)
+        return "Resume and job description processed. Starting the interview.", audio_output
 
     def conduct_interview(self, audio_file):
         if not self.interview_active:
-            return "Please upload your resume and job description first.", ""
+            return "Please upload your resume and job description first.", None
 
         # Transcribe audio
         transcription = stt_model(audio_file)["text"]
         if not transcription.strip():
-            return "No audio detected. Please try again.", ""
+            return "No audio detected. Please try again.", None
 
         # Generate next question
         question = generate_question(transcription, self.resume_embeddings)
-        speak_text(question)
-        return transcription, question
+        audio_output = generate_audio(question)
+        return transcription, audio_output
 
     def end_interview(self):
         self.interview_active = False
-        speak_text("Thank you for participating in the interview. Goodbye!")
-        return "Interview ended. Thank you for participating."
+        audio_output = generate_audio("Thank you for participating in the interview. Goodbye!")
+        return "Interview ended. Thank you for participating.", audio_output
 
 mock_interview = MockInterview()
 
 def upload_inputs(resume, job_desc):
     return mock_interview.upload_inputs(resume, job_desc)
 
-def start_interview():
-    return mock_interview.start_interview()
-
 def conduct_interview(audio_file):
     return mock_interview.conduct_interview(audio_file)
 
@@ -120,13 +109,13 @@ Upload your resume and job description, then engage in a realistic audio-based i
     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")
+        question_output = gr.Audio(label="Question Audio")
         submit_button = gr.Button("Submit Response")
         end_button = gr.Button("End Interview")
 
-    upload_button.click(upload_inputs, inputs=[resume_input, job_desc_input], outputs=[question_output])
+    upload_button.click(upload_inputs, inputs=[resume_input, job_desc_input], outputs=[transcription_output, question_output])
     submit_button.click(conduct_interview, inputs=[audio_input], outputs=[transcription_output, question_output])
-    end_button.click(end_interview, outputs=[question_output])
+    end_button.click(end_interview, outputs=[transcription_output, question_output])
 
 if __name__ == "__main__":
     interface.launch()