Update app.py

app.py

@@ -3,7 +3,7 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import torch
 import soundfile as sf
 
-# Load the Wav2Vec2Processor and model correctly
+# Correctly load the Wav2Vec2Processor and model
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-xlsr-53")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-xlsr-53")
 
@@ -15,7 +15,7 @@ def transcribe_audio(audio):
     # Read the audio file
     audio_input, _ = sf.read(audio.name)
     
-    # Process audio input
+    # Process audio input using the processor
     input_values = processor(audio_input, return_tensors="pt").input_values
     
     # Get model logits (raw prediction)
@@ -36,3 +36,4 @@ iface = gr.Interface(fn=transcribe_audio,
                      
 iface.launch()
 
+