Raphael Lenain
Raphael Lenain
Fixed with ``` pip install torch==2.0.1 pip install wavmark==0.0.3 ```
Hi there -- I have trained a PL-BERT model on a 14 language dataset which was crowdsourced by the author of the paper. You can find this model open-sourced here:...
I'm not sure -- you can see a sample here (the data is from this dataset: https://huggingface.co/datasets/styletts2-community/multilingual-phonemes-10k-alpha/viewer/zh).
i tend to keep some english in the dataset (~5 hours) and have had success with as little as 20 hours of Spanish data split across 4 speakers
https://huggingface.co/papercup-ai/multilingual-pl-bert
Unfortunately because of the privacy policy of the samples that I trained on, I cannot share these samples here. What I can say is that the quality is very much...
@sch0ngut Generally for 50k-100k iterations, whatever that means in terms of epochs for the size of your dataset. But you should be following the validation curve.
You can probably just finetune StyleTTS2 without changing the PL-BERT model, and it would work, with the right data and amount of data. If you want to train PL-BERT on...
the data here (https://huggingface.co/datasets/styletts2-community/multilingual-pl-bert) has been tokenized using the tokenizer of the `bert-multilingual-base-cased` model: https://huggingface.co/google-bert/bert-base-multilingual-cased
@jasonppy thanks a lot for your answers. Do you have a rough idea of what a good validation loss to attain is? For example if you know roughly where you...