Christian Schäfer
Christian Schäfer
Hi, these context dependencies are generally not easy to solve. One option could be to train the model on n-grams of words (e.g. produce training data with 3 words at...
Hi, glad it's been working for you. If there is a lot of ambiguity I would say it could work if you feed the whole sentences, albeit quite memory hungry....
Hi, you can just extract it from the training data. E.g. you collect the set of characters from it and then paste the result into the config. That's basically how...
Hi, you can use the standard config file, but you will have to adjust the language and: text_symbols phoneme_symbols according to the symbols that occur in your dataset!
Nice, let me know if you run into issues.
Hi, multiple characters shouldn't be a problem, the cmudict model has multi-char phonemes: https://github.com/as-ideas/DeepPhonemizer#:~:text=en_us_cmudict_forward You can pass each sample as a tuple of [str, str, list], e.g. ('en', 'word', ['p',...
No that should be fine. Actually your example looks more like there should be three phoneme chars as output instead of a single phoneme instance incorporating all three chars (t͡ʃ)....
Yes, that's also how the standard config is set. You can then simply provide the phonemized words as strings.
Hi, thanks for mentioning the problem. I actually have seen that issue in the past but didn't have time to address it. The problem is not overfitting but the decoding...
Do you mean cross-attention?