update temp folder path

wav2lip/inference.py

@@ -25,7 +25,7 @@ parser.add_argument('--static', type=bool,
 parser.add_argument('--fps', type=float, help='Can be specified only if input is a static image (default: 25)',
                     default=25., required=False)
 
-parser.add_argument('--pads', nargs='+', type=int, default=[0, 10, 0, 0],
+parser.add_argument('--pads', nargs='+', type=int, default=[0, 20, 0, 0],
                     help='Padding (top, bottom, left, right). Please adjust to include chin at least')
 
 parser.add_argument('--face_det_batch_size', type=int,
@@ -56,6 +56,8 @@ args.img_size = 96
 if os.path.isfile(args.face) and args.face.split('.')[1] in ['jpg', 'png', 'jpeg']:
     args.static = True
 
+folder_path = os.path.dirname(args.outfile)
+
 
 def get_smoothened_boxes(boxes, T):
     for i in range(len(boxes)):
@@ -91,7 +93,7 @@ def face_detect(images):
     pady1, pady2, padx1, padx2 = args.pads
     for rect, image in zip(predictions, images):
         if rect is None:
-            cv2.imwrite('temp/faulty_frame.jpg', image)  # check this frame where the face was not detected.
+            cv2.imwrite(f'{folder_path}/faulty_frame.jpg', image)  # check this frame where the face was not detected.
             raise ValueError('Face not detected! Ensure the video contains a face in all the frames.')
 
         y1 = max(0, rect[1] - pady1)
@@ -224,10 +226,10 @@ def main():
 
     if not args.audio.endswith('.wav'):
         print('Extracting raw audio...')
-        command = 'ffmpeg -y -i {} -strict -2 {}'.format(args.audio, 'temp/temp.wav')
+        command = 'ffmpeg -y -i {} -strict -2 {}'.format(args.audio, f'{folder_path}/temp.wav')
 
         subprocess.call(command, shell=True)
-        args.audio = 'temp/temp.wav'
+        args.audio = f'{folder_path}/temp.wav'
 
     wav = audio.load_wav(args.audio, 16000)
     mel = audio.melspectrogram(wav)
@@ -262,7 +264,7 @@ def main():
             print("Model loaded")
 
             frame_h, frame_w = full_frames[0].shape[:-1]
-            out = cv2.VideoWriter('/tmp/result.avi',
+            out = cv2.VideoWriter(f'{folder_path}/result.avi',
                                   cv2.VideoWriter_fourcc(*'DIVX'), fps, (frame_w, frame_h))
 
         img_batch = torch.FloatTensor(np.transpose(img_batch, (0, 3, 1, 2))).to(device)
@@ -282,7 +284,7 @@ def main():
 
     out.release()
 
-    command = 'ffmpeg -y -i {} -i {} -strict -2 -q:v 1 {}'.format(args.audio, '/tmp/result.avi', args.outfile)
+    command = 'ffmpeg -y -i {} -i {} -strict -2 -q:v 1 {}'.format(args.audio, f'{folder_path}/result.avi', args.outfile)
     subprocess.call(command, shell=platform.system() != 'Windows')