Update app.py

app.py

@@ -4,7 +4,7 @@ import gradio as gr
 import torch
 import transformers
 import librosa
-import cv2
+#import cv2
 import numpy as np
 
 # Load models
@@ -63,46 +63,46 @@ def audio_to_video(input):
   output = gr.outputs.Video.from_str(output)
   return output
 
-def image_to_text(input):
-  input = cv2.imread(input)
-  input = cv2.cvtColor(input, cv2.COLOR_BGR2RGB)
-  input = np.expand_dims(input, axis=0)
-  output = image_model(input)
-  return output[0]["label"]
-
-def image_to_audio(input):
-  input = cv2.imread(input)
-  input = cv2.cvtColor(input, cv2.COLOR_BGR2RGB)
-  input = np.expand_dims(input, axis=0)
-  output = image_model(input)
-  output = gr.outputs.Audio.from_str(output[0]["label"])
-  return output
+#def image_to_text(input):
+#  input = cv2.imread(input)
+#  input = cv2.cvtColor(input, cv2.COLOR_BGR2RGB)
+#  input = np.expand_dims(input, axis=0)
+#  output = image_model(input)
+#  return output[0]["label"]
+
+#def image_to_audio(input):
+#  input = cv2.imread(input)
+#  input = cv2.cvtColor(input, cv2.COLOR_BGR2RGB)
+#  input = np.expand_dims(input, axis=0)
+#  output = image_model(input)
+#  output = gr.outputs.Audio.from_str(output[0]["label"])
+#  return output
 
 def image_to_image(input):
   return input
 
-def image_to_video(input):
-  input = cv2.imread(input)
-  input = cv2.cvtColor(input, cv2.COLOR_BGR2RGB)
-  input = np.expand_dims(input, axis=0)
-  output = image_model(input)
-  output = gr.outputs.Video.from_str(output[0]["label"])
-  return output
-
-def video_to_text(input):
-    input = cv2.VideoCapture(input)
-    frames = []
-    while input.isOpened():
-        ret, frame = input.read()
-        if ret:
-            frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-            frames.append(frame)
-        else:
-            breakpoint
-    input.release()
-    frames = np.array(frames)
-    output = video_model(frames)
-    return output[0]["label"]
+#def image_to_video(input):
+#  input = cv2.imread(input)
+#  input = cv2.cvtColor(input, cv2.COLOR_BGR2RGB)
+#  input = np.expand_dims(input, axis=0)
+#  output = image_model(input)
+#  output = gr.outputs.Video.from_str(output[0]["label"])
+#  return output
+
+#def video_to_text(input):
+#    input = cv2.VideoCapture(input)
+#    frames = []
+#    while input.isOpened():
+#        ret, frame = input.read()
+#        if ret:
+#            frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+#            frames.append(frame)
+#        else:
+#            breakpoint
+#    input.release()
+#    frames = np.array(frames)
+#    output = video_model(frames)
+#    return output[0]["label"]
 
 #Output switches