Create app.py

app.py

@@ -16,8 +16,11 @@ st.success("Models loaded successfully!")
 
 # TTS function
 def text_to_speech(text):
+    # Generate mel spectrogram
     mel_output, mel_length, alignment = tacotron2.encode_text(text)
-    waveforms, _, _ = hifi_gan.decode_batch(mel_output)
+    # Decode mel spectrogram to waveform
+    waveforms = hifi_gan.decode_batch(mel_output)
+    # Save waveform as audio file
     audio_path = "output.wav"
     write(audio_path, 22050, waveforms.squeeze(1).cpu().numpy())
     return audio_path
@@ -29,7 +32,10 @@ text = st.text_input("Enter text to convert to speech:")
 if st.button("Generate Speech"):
     if text.strip():
         st.write("Generating speech...")
-        audio_file = text_to_speech(text)
-        st.audio(audio_file, format="audio/wav")
+        try:
+            audio_file = text_to_speech(text)
+            st.audio(audio_file, format="audio/wav")
+        except Exception as e:
+            st.error(f"Error during TTS generation: {e}")
     else:
         st.warning("Please enter some text.")