Update app.py

app.py

@@ -5,6 +5,7 @@ from moviepy.editor import *
 import cv2
 import librosa
 
+
 def get_optimal_font_scale(text, width):
     for scale in reversed(range(0, 60, 1)):
         textSize = cv2.getTextSize(text, fontFace=cv2.FONT_HERSHEY_DUPLEX, fontScale=scale/10, thickness=1)
@@ -16,9 +17,7 @@ def get_optimal_font_scale(text, width):
 
 processor = Wav2Vec2Processor.from_pretrained("facebook/hubert-xlarge-ls960-ft")
 model = HubertForCTC.from_pretrained("facebook/hubert-xlarge-ls960-ft")
-#def map_to_array(file):
-    #speech, _ = sf.read(file)
-    #return speech
+
 def inference(audio, image):
     y, sr = librosa.load(audio.name,sr=16000)
     input_values = processor(y, return_tensors="pt").input_values  # Batch size 1