Update app.py

app.py

@@ -1,20 +1,20 @@
-from spleeter import Splitter
-import torchaudio
-from torchaudio.transforms import Resample
-import torch
-import gradio as gr
-def separate(audio_path):
-    model = Splitter(2)
-    wav, sr = torchaudio.load(audio_path)
-    target_sr = 44100
-    if sr != target_sr:
-        resampler = Resample(sr, target_sr)
-        wav = resampler(wav)
-        sr = target_sr
-    with torch.no_grad():
-        results = model.forward(wav)
-        torchaudio.save("vocals.mp3", results['vocals'], sr,format="mp3")
-        torchaudio.save("accompaniment.mp3", results['accompaniment'], sr,format="mp3")
-    return "vocals.mp3" , "accompaniment.mp3"
-
-gr.Interface(separate, gr.Audio(type="filepath"), [gr.Audio(type="filepath"), gr.Audio(type="filepath")]).launch()
+from spleeter import Splitter
+import torchaudio
+from torchaudio.transforms import Resample
+import torch
+import gradio as gr
+def separate(inst,audio_path,progress=gr.Progress(True)):
+    model = Splitter(inst)
+    wav, sr = torchaudio.load(audio_path)
+    target_sr = 44100
+    if sr != target_sr:
+        resampler = Resample(sr, target_sr)
+        wav = resampler(wav)
+        sr = target_sr
+    with torch.no_grad():
+        results = model.forward(wav)
+    for i in results:
+        torchaudio.save(f"{i}.mp3", results[i], sr,format="mp3")
+    return tuple([i+".mp3" for i in results] + [None for _ in range(5-len(results))])
+
+gr.Interface(separate, gr.Dropdown([2,4,5]),gr.Audio(type="filepath"), [gr.Audio(type="filepath"), gr.Audio(type="filepath"),gr.Audio(type="filepath"),gr.Audio(type="filepath"),gr.Audio(type="filepath")]).launch()