Update app.py

app.py

@@ -18,6 +18,9 @@ def correct_casing(input_sentence):
     return ' '.join([s.replace(s[0], s[0].capitalize(), 1) for s in sentences])
 
 def asr_transcript(audio):
+    if audio is None or len(audio) == 0:
+        return ""
+    
     # Process the audio
     input_values = processor(audio, sampling_rate=16000, return_tensors="pt").input_values
     # Get logits
@@ -31,15 +34,18 @@ def asr_transcript(audio):
     return transcription
 
 def real_time_asr(audio, state=""):
-    audio = np.array(audio)
-    transcription = asr_transcript(audio)
-    state += " " + transcription
-    return state, state
+    try:
+        audio = np.array(audio)
+        transcription = asr_transcript(audio)
+        state += " " + transcription
+        return state, state
+    except Exception as e:
+        return str(e), state
 
 # Create the Gradio interface
 iface = gr.Interface(
     fn=real_time_asr,
-    inputs=[gr.Audio(streaming=True), gr.State()],
+    inputs=[gr.Audio(source="microphone", streaming=True), gr.State()],
     outputs=[gr.Textbox(), gr.State()],
     live=True,
     title="Real-Time ASR using Wav2Vec 2.0",