Update app.py

app.py

@@ -19,8 +19,7 @@ def speech_file_to_array_fn(path, sampling_rate):
     return speech
 
 
-def predict(path, sampling_rate):
-    speech = speech_file_to_array_fn(path, sampling_rate)
+def predict(speech, sampling_rate):
     inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
     inputs = {key: inputs[key].to(device) for key in inputs}
 
@@ -43,18 +42,15 @@ model.to(device)
 
 
 def transcribe(audio):
-    filename = audio.split("/")[-1]
-    print(filename, f"c_{filename}")
-    command = f"sox -t wav /tmp/{filename} -r 16000 -b 16 /tmp/c_{filename} channels 1"
-    subprocess.call(command, shell=True)
-    return predict(f"/tmp/c_{filename}", 16000)
+    print(audio.shape)
+    return predict(audio, 16000)
 
 
 def get_asr_interface():
     return gr.Interface(
         fn=transcribe, 
         inputs=[
-            gr.inputs.Audio(source="microphone", type="filepath")
+            gr.inputs.Audio(source="microphone", type="numpy")
         ],
         outputs=[
             "textbox"