Update app.py

app.py

@@ -22,14 +22,6 @@ import numpy as np
 # from IPython.display import Audio
 
 import torch
-import torchaudio
-from speechbrain.pretrained import SpectralMaskEnhancement
-
-enhance_model = SpectralMaskEnhancement.from_hparams(
-source="speechbrain/metricgan-plus-voicebank",
-savedir="pretrained_models/metricgan-plus-voicebank",
-run_opts={"device":"cuda"},
-)
 
 from TTS.tts.utils.synthesis import synthesis
 from TTS.tts.utils.text.symbols import make_symbols, phonemes, symbols
@@ -171,15 +163,7 @@ def voice_conversion(ta, ra, da):
   # print("Reference Audio after decoder:")
   # IPython.display.display(Audio(ref_wav_voc, rate=ap.sample_rate))
 
-  noisy = enhance_model.load_audio(
-  ref_wav_voc
-  ).unsqueeze(0)
-
-  enhanced = enhance_model.enhance_batch(noisy, lengths=torch.tensor([1.]))
-  torchaudio.save("enhanced.wav", enhanced.cpu(), 16000)
-
-  return "enhanced.wav"
-
+  return (ap.sample_rate, ref_wav_voc)
 
 def generate_text_to_speech(text_prompt, selected_speaker, text_temp, waveform_temp):
     audio_array = generate_audio(text_prompt, selected_speaker, text_temp, waveform_temp)
@@ -262,7 +246,7 @@ with gr.Blocks() as demo:
     )
     gr.Markdown(
             """ 
-### 😄 - You may also apply [VoiceFixer](https://huggingface.co/spaces/Kevin676/VoiceFixer) to the generated audio in order to enhance the speech.
+## 😄 - You may also apply [VoiceFixer](https://huggingface.co/spaces/Kevin676/VoiceFixer) to the generated audio in order to enhance the speech.
 ## 🌎 Foreign Language
 Bark supports various languages out-of-the-box and automatically determines language from input text. \
 When prompted with code-switched text, Bark will even attempt to employ the native accent for the respective languages in the same voice.