This model has been trained from scratch with my customized dataset mbarnig/lb-de-fr-en-pt-12800-TTS_CORPUS and the 🐸 Coqui-TTS multilingual VITS-model recipe (version 0.7.1). The model was trained without phonemes with the following character-set:
characters="abcdefghijklmnopqrstuvwxyz ßàáâãäçèéêëíîïóôõöùúûü",
punctuations="!'(),-.:;? ",
phonemes=None,
A live inference-demo of the model is available in my HuggingFace space ⌨️ 🇱🇺 🔈 mbarnig/lb_de_fr_en_pt_COQUI_VITS_TTS.
Click the tab training metrics above to view the live Tensorboard of the model training.
