ylacombe

This is a finetuned version of the Spanish version of Massively Multilingual Speech (MMS) models, which are light-weight, low-latency TTS models based on the VITS architecture. It was trained in around 20 minutes with as little as 80 to 150 samples, on this Colombian Spanish dataset. Training recipe available in this github repository: ylacombe/finetune-hf-vits. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Example: Generate Spanish speech with `ylacombe/mms-spa-finetuned-colombian-monospeaker`. Optionally, save the audio to a wav file (Node.js):