Update app.py

app.py

@@ -4,13 +4,14 @@ from transformers import pipeline
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 import PyPDF2
-import torch
-import gc
+from TTS.api import TTS  # Coqui TTS library
+
+# Initialize TTS model
+tts_model = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=False)
 
 # Load local models for inference
-stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-small", torch_dtype=torch.float16)
-conversation_model = pipeline("text-generation", model="facebook/blenderbot-400M-distill", torch_dtype=torch.float16)
-tts_model = pipeline("text-to-speech", model="facebook/fastspeech2-en-ljspeech", torch_dtype=torch.float16)
+stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-base")
+conversation_model = pipeline("text-generation", model="facebook/blenderbot-400M-distill")
 
 # Load a pre-trained model for vector embeddings
 embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
@@ -49,9 +50,10 @@ def generate_question(user_input, resume_embeddings):
 
 # Generate TTS output
 def generate_audio(text):
-    """Convert text to audio using Hugging Face TTS model."""
-    audio_data = tts_model(text, return_tensors=True)["waveform"]
-    return audio_data
+    """Convert text to audio using Coqui TTS."""
+    audio_path = "output.wav"
+    tts_model.tts_to_file(text=text, file_path=audio_path)
+    return audio_path
 
 # Gradio interface
 class MockInterview:
@@ -120,4 +122,4 @@ Upload your resume and job description, then engage in a realistic audio-based i
     end_button.click(end_interview, outputs=[transcription_output, question_output])
 
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()