NameError: name 'finout_image_path' is not defined

[AshenJie6]

[info] Step1: Prepare input data ... ==> detect face landmarks ... 0it [00:00, ?it/s] ==> face align ... 0it [00:00, ?it/s] [info] Step2: load model ... Load checkpoint from: ./checkpoint/lip-clarity-model.pth [info] Step3: save results ... ./test_result/00001/audio.wav: No such file or directory [info] Step4: Inver Affine Transform (Being here means wearing paste back) ... ==> paste background ... 0it [00:00, ?it/s] Traceback (most recent call last): File "inference.py", line 304, in os.system(synthesis_CMD.format(wav_path, finout_image_path, result_path, "result", video_basename)) NameError: name 'finout_image_path' is not defined

My input_video is /sample/00001.mp4. This error occurs after I execute inference.py And my _align_crop_image、full_frame、imageconfig、landmarks folders are all empty, how can I solve this problem? thnak you.

[TalhaaaYaqoob]

solved it! if you are using Nvidia gpu edit these lines split_image_cmd = 'ffmpeg -hwaccel cuda -hide_banner -y -i {} -r 25 {}/%05d.png' split_wav_cmd = 'ffmpeg -hwaccel cuda -hide_banner -y -i {} -async 1 -ac 1 -vn -acodec pcm_s16le -ar 16000 {}'

[yylgoodlucky]

Sorry，I just saw your issue, good lucky to you solved it .

[Chechgroup]

solved it! if you are using Nvidia gpu edit these lines split_image_cmd = 'ffmpeg -hwaccel cuda -hide_banner -y -i {} -r 25 {}/%05d.png' split_wav_cmd = 'ffmpeg -hwaccel cuda -hide_banner -y -i {} -async 1 -ac 1 -vn -acodec pcm_s16le -ar 16000 {}'

I have the same problem... please help. My telegram the_best

[Chechgroup]

Sorry，I just saw your issue, good lucky to you solved it .

hi help me please... I have the same problem... please help. My telegram the_best

[Chechgroup]

solved it! if you are using Nvidia gpu edit these lines split_image_cmd = 'ffmpeg -hwaccel cuda -hide_banner -y -i {} -r 25 {}/%05d.png' split_wav_cmd = 'ffmpeg -hwaccel cuda -hide_banner -y -i {} -async 1 -ac 1 -vn -acodec pcm_s16le -ar 16000 {}'

help me please