diff --git a/SyncNetInstance.py b/SyncNetInstance.py
index 497d44f..1b08504 100644
--- a/SyncNetInstance.py
+++ b/SyncNetInstance.py
@@ -39,7 +39,7 @@ def __init__(self, dropout = 0, num_layers_in_fc_layers = 1024):
 
         self.__S__ = S(num_layers_in_fc_layers = num_layers_in_fc_layers).cuda();
 
-    def evaluate(self, opt, videofile):
+    def evaluate(self, opt, videofile, verbose=True):
 
         self.__S__.eval();
 
@@ -52,11 +52,27 @@ def evaluate(self, opt, videofile):
 
         os.makedirs(os.path.join(opt.tmp_dir,opt.reference))
 
-        command = ("ffmpeg -y -i %s -threads 1 -f image2 %s" % (videofile,os.path.join(opt.tmp_dir,opt.reference,'%06d.jpg'))) 
-        output = subprocess.call(command, shell=True, stdout=None)
-
-        command = ("ffmpeg -y -i %s -async 1 -ac 1 -vn -acodec pcm_s16le -ar 16000 %s" % (videofile,os.path.join(opt.tmp_dir,opt.reference,'audio.wav'))) 
-        output = subprocess.call(command, shell=True, stdout=None)
+        jpg_template = os.path.join(opt.tmp_dir, opt.reference, '%06d.jpg')
+        wav_path = os.path.join(opt.tmp_dir, opt.reference, 'audio.wav')
+
+        # 1) extract frames
+        cmd = [
+            "ffmpeg", "-loglevel", "error", "-nostats",
+            "-y", "-i", videofile,
+            "-vf", "scale=224:224:flags=bilinear,setsar=1",  # ← FIXED: added -vf and fixed argument
+            "-threads", "1",
+            "-f", "image2", jpg_template
+        ]
+        subprocess.run(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False)
+
+        # 2) extract audio
+        cmd = [
+            "ffmpeg", "-loglevel", "error", "-nostats",
+            "-y", "-i", videofile,
+            "-async", "1", "-ac", "1", "-vn",
+            "-acodec", "pcm_s16le", "-ar", "16000", wav_path
+        ]
+        subprocess.run(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False)
         
         # ========== ==========
         # Load video 
@@ -91,7 +107,7 @@ def evaluate(self, opt, videofile):
         # Check audio and video input length
         # ========== ==========
 
-        if (float(len(audio))/16000) != (float(len(images))/25) :
+        if (float(len(audio))/16000) != (float(len(images))/25) and  verbose :
             print("WARNING: Audio (%.4fs) and video (%.4fs) lengths are different."%(float(len(audio))/16000,float(len(images))/25))
 
         min_length = min(len(images),math.floor(len(audio)/640))
@@ -123,8 +139,8 @@ def evaluate(self, opt, videofile):
         # ========== ==========
         # Compute offset
         # ========== ==========
-            
-        print('Compute time %.3f sec.' % (time.time()-tS))
+        if verbose:
+            print('Compute time %.3f sec.' % (time.time()-tS))
 
         dists = calc_pdist(im_feat,cc_feat,vshift=opt.vshift)
         mdist = torch.mean(torch.stack(dists,1),1)
@@ -140,9 +156,10 @@ def evaluate(self, opt, videofile):
         fconfm  = signal.medfilt(fconf,kernel_size=9)
         
         numpy.set_printoptions(formatter={'float': '{: 0.3f}'.format})
-        print('Framewise conf: ')
-        print(fconfm)
-        print('AV offset: \t%d \nMin dist: \t%.3f\nConfidence: \t%.3f' % (offset,minval,conf))
+        if verbose:
+            print('Framewise conf: ')
+            print(fconfm)
+            print('AV offset: \t%d \nMin dist: \t%.3f\nConfidence: \t%.3f' % (offset,minval,conf))
 
         dists_npy = numpy.array([ dist.numpy() for dist in dists ])
         return offset.numpy(), conf.numpy(), dists_npy