Update app.py

app.py

@@ -3,6 +3,7 @@ subprocess.run(["pip", "install", "gradio", "--upgrade"])
 subprocess.run(["pip", "install", "transformers"])
 subprocess.run(["pip", "install", "torchaudio", "--upgrade"])
 
+
 import gradio as gr
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import torchaudio
@@ -13,22 +14,29 @@ model = Wav2Vec2ForCTC.from_pretrained("jonatasgrosman/wav2vec2-large-xlsr-53-it
 
 # Function to perform ASR on audio data
 def transcribe_audio(audio_data):
-    # Convert audio data to mono and normalize
-    audio_data = torchaudio.transforms.Resample(audio_data[1], 16000)(audio_data[0])
-    audio_data = torchaudio.functional.gain(audio_data, gain_db=5.0)
+    if audio_data is None:
+        return "No audio data received."
+
+    try:
+        # Convert audio data to mono and normalize
+        audio_data = torchaudio.transforms.Resample(audio_data[1], 16000)(audio_data[0])
+        audio_data = torchaudio.functional.gain(audio_data, gain_db=5.0)
+
+        # Apply custom preprocessing to the audio data if needed
+        input_values = processor(audio_data[0].numpy(), return_tensors="pt").input_values
 
-    # Apply custom preprocessing to the audio data if needed
-    input_values = processor(audio_data[0].numpy(), return_tensors="pt").input_values
+        # Perform ASR
+        with torch.no_grad():
+            logits = model(input_values).logits
 
-    # Perform ASR
-    with torch.no_grad():
-        logits = model(input_values).logits
+        # Decode the output
+        predicted_ids = torch.argmax(logits, dim=-1)
+        transcription = processor.batch_decode(predicted_ids)
 
-    # Decode the output
-    predicted_ids = torch.argmax(logits, dim=-1)
-    transcription = processor.batch_decode(predicted_ids)
+        return transcription[0]
 
-    return transcription[0]
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
 
 # Create Gradio interface
 audio_input = gr.Audio()