Spanish tokenizer
Hello! Amazing work doing all of this!
I want to share the spanish tokenizer I trained, it sounds not bad at all, I expect to train a new one with better literature but this one works quite fine.
Here is the repo: Lancer1408/bark-es-tokenizer
Awesome! You can make a PR on github at https://github.com/gitmylo/Voice-cloning-quantizers adding it to the list, so it will automatically be available for use in Audio-Webui. The template.json contains the template code, just add it to the list!
If you have the dataset, you can upload it on HuggingFace as well. You can add this under the extra section. If not, you can keep the extra section empty. (It would really be appreciated though, once enough datasets have been made, i can train a multilingual quantizer, which should work great with every language that is supported!)