Quick question: where do the pretrained model's phoneme dictionaries come from?

[ADD-eNavarro]

Hi!

Great work you're doing here. I've been testing your tool, it's easy to use and gives fine results. Since I'm looking for a tool to generate a phonemized imput for the VITS model (in onnx format), I need to use the same tokenizer (phonemizer) that model espects. I've found that your pretrained models already have the dictionary embedded in them. Can I ask where did those dictionaries come from? In your colab training example you use CUNY-CL/wikipron's ones, but I was wondering if those are the ones you used originally or just in the example.

Thanks.

[NextDevX]

Hi,

Have you found a way to convert the deep phonemizer module to onnx format and use it?

[ADD-eNavarro]

I'm afraid I didn't. I mean, nobody answered my question, so there was nowhere else for me to go. I just let down VITS.

[NextDevX]

@ADD-eNavarro

[Is There a Sample Showing How to Convert to ONNX?](https://github.com/as-ideas/DeepPhonemizer/issues/41#issuecomment-2116241220)