Open KTXKIKI opened 9 months ago
@KTXKIKI
Thank you for provided information, but it is not clear what we are supposed to do with that. It was not implemented not because we do not have references, but because now it is not our priority.
If you want to help, you may create aggregated feature request regarding 3D features you would like to have, decsribing examples, use-cases and concepts. What do you think?
Speaking about voice ASR, I do not think its relevant for now. It is even less priority than 3D and multi-modal CVAT data scenarious.
Oh, oh, I want to help you. The CVAT team hopes that CVAT will become the number one in the field of computer vision annotation. I don't have strong abilities, but I am still working hard to learn. If my abilities are sufficient, I will be very willing to develop and contribute code together. In the future, if I have enough funds, I will also be very willing to become a paid version of the enterprise. I hope CVAT will become stronger and stronger @bsekachev
Voice ASR
https://github.com/PaddlePaddle/PaddleSpeech https://github.com/nl8590687/ASRT_SpeechRecognition https://github.com/nobody132/masr https://github.com/espnet/espnet https://github.com/wenet-e2e/wenet https://github.com/mozilla/DeepSpeech
natural language entity extraction NLP https://github.com/hankcs/pyhanlp
2-3D point cloud and pure 3D point cloud segmentation https://github.com/PJLab-ADG/SensorsCalibration https://github.com/walzimmer/3d-bat https://github.com/Hitachi-Automotive-And-Industry-Lab/semantic-segmentation-editor