Update app.py

app.py

@@ -8,6 +8,15 @@ from voicefixer import VoiceFixer
 voicefixer = VoiceFixer()
 import gradio as gr
 import openai
+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"},
+)
 
 mes1 = [
     {"role": "system", "content": "You are a TOEFL examiner. Help me improve my oral Englsih and give me feedback."}
@@ -72,7 +81,16 @@ def transcribe(apikey, upload, audio, choice1):
                     cuda=True, # whether to use gpu acceleration
                     mode = 0) # You can try out mode 0, 1 to find out the best result
 
-    return [result.text, chat_response, "audio1.wav"]
+
+
+    noisy = enhance_model.load_audio(
+    "audio1.wav"
+    ).unsqueeze(0)
+
+    enhanced = enhance_model.enhance_batch(noisy, lengths=torch.tensor([1.]))
+    torchaudio.save("enhanced.wav", enhanced.cpu(), 16000)
+
+    return [result.text, chat_response, "enhanced.wav"]
 
 output_1 = gr.Textbox(label="Speech to Text")
 output_2 = gr.Textbox(label="ChatGPT Output")