Problems to test-model with cli about deep-speaker

[philipperemy]

@asr-lord hummm. First did the examples and the CLI work with the checkpoint I provided in the README (with your python configuration)?

[asr-lord]

@asr-lord hummm. First did the examples and the CLI work with the checkpoint I provided in the README (with your python configuration)?

In both cases didn't work: with the checkpoint and with my trained model.

[philipperemy]

@asr-lord can you paste all the commands to reproduce the issue?

[asr-lord]

@asr-lord can you paste all the commands to reproduce the issue?

./deep-speaker download_librispeech 
./deep-speaker build_mfcc
export CUDA_VISIBLE_DEVICES=0; python cli.py test-model --working_dir ~/.deep-speaker-wd/triplet-training/ --checkpoint_file checkpoint
s-triplets/ResCNN_checkpoint_37.h5

[philipperemy]

Thank you

[philipperemy]

@asr-lord sorry for the late reply. There's definitely something. You are right. I'm trying to find a way to fix it.

[philipperemy]

Okay that's a tensorflow issue. If you use tensorflow==2.3 it works. It breaks after tensorflow 2.4. It's a bit weird because the example in the README works well with tensorflow 2.7.

[philipperemy]

I will close this issue and mention it in the README.