Closed choclatier closed 3 years ago
Found out the problem was the training couldn't handle sentence cased training examples. After uppercasing all training examples the model finally started to train. I thought the tokenizer would take care of this or some preprocessing step. The documentation should probably mention this or further explain this.
❓ Questions and Help
I'm trying to train on the timit test dataset for a sanity check, but it seems the more I train on this set the worse the model gets. I tried with one epoch, its gets slightly worse. With 10 its inferences nothing or
<unk>
tokens. I also have a larger dataset I tried tofit
the data to, and get< val_score: inf >
I can't tell if my libraries are somehow corrupted. I was able to actually fiddle around and successfully finetune once out of a 150 runs. I still can't reproduce the model. Is there a test I can do to ensure that there is some sort of learning happening? How can I check that that the model weights were actually trained to some degree, better or worse? I'm also suspect that after installing Kaldi there were somec
libraries that were possibly replaced out, could this be an issue? It might be coincidence but I think after that was I not able to reproduce the model.Code
Console
What's your environment?