Closed nastia-lado closed 10 months ago
Hi @nastia-lado, can you please share the colab code with me so I can reproduce the error you have?
Hi @mpc001! Here is the link to colab: https://colab.research.google.com/drive/1SScL2-8IwnGtjqNnwmr3jSDqWc-Hx4-t?usp=sharing
But I didn't change anything in the lines that you recommend for demo. I just included !
to run it from colab.
Hi @nastia-lado, thank you for sharing. I can reproduce the issue. The issue can be fixed by replace data.modality=['audio']
to data.modality='audio'
. Please let me know if there are any issues.
Thanks a lot! I read that there is a plan to release audiovisual models, and I saw the option to select it in the code. But as far as I understood the model is still not available, right?
Hi @nastia-lado, you are right; the pre-trained model has been released on Visual_Speech_Recognition_for_Multiple_Languages. Feel free to check it. However, it has not been included in this repository since the training code has not yet been released.
Thanks a lot!
hello @mpc001 , a small typo, in https://github.com/mpc001/auto_avsr/blob/main/demo.py#L30, you may want to change visual to video. Thanks!
Hi!
Thanks a lot for the model. I try to run AVSR model in colab using demo.py. I'm using asr_trlrwlrs2lrs3vox2avsp_base.pth and I've specified the modality as
'audiovisual'
. I'm getting this error:I tried also specifying
['audio', 'video']
but that doesn't seem right.