add app.py

app.py

@@ -1,7 +1,9 @@
 import gradio as gr
+import numpy as np
 import torch
 import torchaudio
 from denoisers import WaveUNetModel
+from tqdm import tqdm
 
 MODEL = WaveUNetModel.from_pretrained("wrice/waveunet-vctk-24khz")
 
@@ -23,7 +25,7 @@ def denoise(inputs):
     padded = torch.nn.functional.pad(audio, (0, padding))
 
     clean = []
-    for i in range(0, padded.shape[-1], chunk_size):
+    for i in tqdm(range(0, padded.shape[-1], chunk_size)):
         audio_chunk = padded[:, i : i + chunk_size]
         with torch.no_grad():
             clean_chunk = MODEL(audio_chunk[None]).logits
@@ -34,7 +36,7 @@ def denoise(inputs):
 
     print(f"Denoised shape: {denoised.shape}")
 
-    return MODEL.config.sample_rate, denoised
+    return MODEL.config.sample_rate, denoised[np.newaxis, :]
 
 
 iface = gr.Interface(fn=denoise, inputs="audio", outputs="audio")

requirements.txt

@@ -7,3 +7,4 @@ denoisers
 transformers
 librosa
 wandb
+tqdm