Update app.py

app.py

@@ -8,12 +8,14 @@ from voicefixer import VoiceFixer
 voicefixer = VoiceFixer()
 import gradio as gr
 import openai
+import torch
 import torchaudio
-from speechbrain.pretrained import WaveformEnhancement
-enhance_model = WaveformEnhancement.from_hparams(
-    source="speechbrain/mtl-mimic-voicebank",
-    savedir="pretrained_models/mtl-mimic-voicebank",
-    run_opts={"device":"cuda"},
+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"},
 )
 
 mes1 = [
@@ -78,10 +80,12 @@ def transcribe(apikey, upload, audio, choice1):
                     cuda=True, # whether to use gpu acceleration
                     mode = 0) # You can try out mode 0, 1, or 2 to find out the best result
     
-    enhanced = enhance_model.enhance_file("audio1.wav")
+    noisy = enhance_model.load_audio(
+    "audio1.wav"
+    ).unsqueeze(0)
 
-    # Saving enhanced signal on disk
-    torchaudio.save("enhanced.wav", enhanced.unsqueeze(0).cpu(), 16000)
+    enhanced = enhance_model.enhance_batch(noisy, lengths=torch.tensor([1.]))
+    torchaudio.save("enhanced.wav", enhanced.cpu(), 16000)
 
     return [result.text, chat_response, "enhanced.wav"]