Steffen Lohrey

Already did that, spaces do not help in this case, but you are right, it's a phonemizer-related problem: ```console >>> import phonemizer >>> print(phonemizer.phonemize("A B C",language='de')) ɑː beː seː ```...

Ok, seems like somehow an old espeak version was still installed on my system and phonemizer used this; after uninstalling the "C"-problem is solved. In the process, I checked how...

thanks for the tips. i found this 48k vocos model: [https://huggingface.co/kittn/vocos-mel-48khz-alpha1](url) i will try to make it work with that.

+1

Ran into the same bug. It seems to originate from line 1008 in compiler.py ``` forward = forward.replace( "loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))", "shift_logits = shift_logits.view(-1, self.config.text_config.vocab_size)\n"\ "shift_labels = shift_labels.view(-1)\n"\...

I am currently working on finetuning the t3 block for german. Looks promising so far. Early tests indicated that the s3 block might need finetuning aswell to get rid of...

So, the finetuning script is working, you can find it here: https://github.com/stlohrey/chatterbox-finetuning Keep in mind that it is WIP and not very clean. I made a german model with it...