HeChengHui
HeChengHui
@narendasan Thank you for the suggestion but i am still getting the same error ``` File "/home/default/anaconda3/envs/driverstate_ttrt/lib/python3.10/site-packages/torch/jit/_recursive.py", line 397, in create_methods_and_properties_from_stubs concrete_type._create_methods_and_properties(property_defs, property_rcbs, method_defs, method_rcbs, method_defaults) RuntimeError: forward(__torch__.spiga.models.cnn.layers.___torch_mangle_24.Residual self, Tensor...
@narendasan any updates?
@apbose i am using the code + weights from this [repo](https://github.com/andresprados/SPIGA). More specifically, this [weight](https://drive.google.com/file/d/1h0qA5ysKorpeDNRXe9oYkVcVe8UYyzP7/view?usp=drive_link)
@apbose i printed out the shape of the inputs from [here](https://github.com/andresprados/SPIGA/blob/a709c95cc93f8246d7bff4cfb970a2dd0d62ffed/spiga/inference/framework.py#L93). ``` def net_forward(self, inputs): for i in inputs: print(i.shape) outputs = self.model(inputs) return outputs ``` I didnt use any...
@RichestYoo did you managed to get it working? i have added `extra_compile_args=['std=c99'],` to FaceBoxes build.py and `os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE" ` to singleImage.py butstuck at `'int_t' but got 'long long'` problem.
@nathfavour Can i check what if the code shared [here ](https://github.com/huggingface/distil-whisper/issues/4#issuecomment-1794494419) is doing the same as what you are doing?
@SaoYear Thank you for your inference code. I tried using my own audio with stage_2_wo_external and i got the following results  is it supposed to do this? the audio...
@SaoYear [mixed.zip](https://github.com/user-attachments/files/16311452/mixed.zip) the audio is >10s but the code seems to handle it by splitting and overlap.
@wondervictor Thank you for adding video support! I have questions regarding the `model.reparameterize(texts)`. 1. Do i have to run this command for every frame? does the model not get configured...
@Suvi-dha Hi, wondering if you managed to solve this problem and willing to share your trained model?