python process.py video/me25.mp4 --asr hubert【cv2.error: OpenCV(4.10.0)】

[mikestut]

detecting landmarks...
[ERROR:[email protected]] global onnx_importer.cpp:1035 handleNode DNN/ONNX: ERROR during processing node with 5 inputs and 1 outputs: [Slice]:(onnx_node!Slice_25) from domain='ai.onnx'
Traceback (most recent call last):
File "/home/tyn/Ultralight-Digital-Human/data_utils/process.py", line 82, in
get_landmark(opt.path, landmarks_dir)
File "/home/tyn/Ultralight-Digital-Human/data_utils/process.py", line 50, in get_landmark
landmark = Landmark()
File "/home/tyn/Ultralight-Digital-Human/data_utils/get_landmark.py", line 76, in init
self.det_net = SCRFD('./scrfd_2.5g_kps.onnx', confThreshold=0.1, nmsThreshold=0.5)
File "/home/tyn/Ultralight-Digital-Human/data_utils/detect_face.py", line 12, in init
self.net = cv2.dnn.readNet(onnxmodel)
cv2.error: OpenCV(4.10.0) /io/opencv/modules/dnn/src/onnx/onnx_importer.cpp:1057: error: (-2:Unspecified error) in function 'handleNode'

Node [[email protected]]:(onnx_node!Slice_25) parse error: OpenCV(4.10.0) /io/opencv/modules/dnn/src/onnx/onnx_importer.cpp:1240: error: (-215:Assertion failed) constBlobs.find(node_proto.input(i)) != constBlobs.end() in function 'parseSlice'