|
发表于 2024-8-6 11:38:37
|
显示全部楼层
有遇到一个问题,每次卡到40%就出错:
Starting...
Processing Wav2Lip: 40%|████████████████▏ | 111/281 [00:59<01:30, 1.87it/s]
Traceback (most recent call last):
File "E:\AI_TOOL\Easy-Wav2Lip\inference.py", line 698, in <module>
main()
File "E:\AI_TOOL\Easy-Wav2Lip\inference.py", line 597, in main
for i, (img_batch, mel_batch, frames, coords) in enumerate(tqdm(
File "E:\AI_TOOL\Easy-Wav2Lip\python310\lib\site-packages\tqdm\std.py", line 1181, in __iter__
for obj in iterable:
File "E:\AI_TOOL\Easy-Wav2Lip\inference.py", line 473, in datagen
face, coords = face_det_results[idx].copy()
IndexError: list index out of range
Processing failed! see line above 👆
Processing failed
已确认文件为视频格式,跳过图片转换视频过程。
Processing muskTest_00.mp4 using muskTest_00.wav for audio
sys.executable:E:\AI_TOOL\Easy-Wav2Lip\python310\python.exe
imports loaded!
analysing audio...
281 frames to process
Using face detection data from last input
mask size: 1.0, feathering: 1
Loading gfpgan
Starting...
Processing Wav2Lip: 40%|████████████████▏ | 111/281 [00:39<00:59, 2.84it/s]
Traceback (most recent call last):
File "E:\AI_TOOL\Easy-Wav2Lip\inference.py", line 698, in <module>
main()
File "E:\AI_TOOL\Easy-Wav2Lip\inference.py", line 597, in main
for i, (img_batch, mel_batch, frames, coords) in enumerate(tqdm(
File "E:\AI_TOOL\Easy-Wav2Lip\python310\lib\site-packages\tqdm\std.py", line 1181, in __iter__
for obj in iterable:
File "E:\AI_TOOL\Easy-Wav2Lip\inference.py", line 473, in datagen
face, coords = face_det_results[idx].copy()
IndexError: list index out of range
Processing failed! see line above 👆
Processing failed |
|