Soroush Hashemifar

Failed to install pykaldi

3

I followed the instructions and ran the following to commands to install pykaldi: ``` git clone https://github.com/pykaldi/pykaldi.git cd pykaldi sudo apt-get install autoconf automake cmake curl g++ git graphviz libatlas3-base...

Object tracking does not work properly

3

I have ran object tracking on multiple videos recorded from streets, but the object tracker does not draw any bounding box on people and cars. The default configuration is used.

finetune.py does not save checkpoints

1

I run the following command to finetune the model: `python finetune.py --transcript_file ./cv-corpus-6.1-2020-12-11/vi/clips/clips.trans.txt --pretrain_model /content/self-supervised-speech-recognition/outputs/2021-06-25/14-39-00/checkpoints/checkpoint_best.pt --dict_file /content/self-supervised-speech-recognition/save_dir/dict.ltr.txt` and I get the following logs: ``` 2021-06-25 15:31:21 | INFO | fairseq_cli.train...

I wanted to know what happens if I train the unsupervised model on unlabelled audios with music and background noise. Will that still work?

Overfitting on CASIA-v2

9

Hi. I tried to finetune your RR-Unet model on CASIA-v2 and CoMoFoD datasets through your repository, but the model overfits. Is this normal?

In this new version, the optimization function can have more than 2 or 3 variables, i.e. infinite number of variables.

Hi. Thank you for this amazing idea on RAG + ImCap. I am wondering if the same approach is applicable to face recognition. Is it possible to have an external...