Yochai Yemini

Hi @Yolanda2020, Can you please send me your solution too?

Just to add - we tried to used Use Case 1 with the [English MFA dictionary v2_0_0](https://mfa-models.readthedocs.io/en/latest/dictionary/English/English%20MFA%20dictionary%20v2_0_0.html#English%20MFA%20dictionary%20v2_0_0) which covers both UK and US English, but this dictionary does not cover...

Did you install the ctcdecode package? Seems like it's missing

Please have a look here https://github.com/parlance/ctcdecode/issues?q=is%3Aissue+is%3Aopen+windows and see if it is of any help

I hope that the repositories that you mentioned can resolve the issue. I've also noticed that there is a relevant PyTorch module https://pytorch.org/audio/main/generated/torchaudio.models.decoder.CTCDecoder.html Unfortunately, I currently don't have the capacity...

Thank you for the quick response! I forgot to mention that I propagated the learnable version of `joint_label` instead of the fixed one so I don't believe this is the...

Wanted to update that I've tried your suggestions but unfortunately the problem still persists. Do you recall perhaps how you implemented it? I double-checked my implementation by taking a fixed...

It gives me the initialised partition, since the gradients are too small to change it

I added the following line to binarise the labels: ``` label[range(len(label)), label.argmax(1)] = 1 label[label < 1] = 0 ``` before ```e = z@ label.T``` but it didn't seem to...

It seems like the loading of weights of the Retina Face Detector model is unsuccessful. Are you sure that you followed the installation instructions of RetinaFace closely?