🔥 Overview
This indonesian finetune of F5-TTS is made to introduce indonesian speech capabilities on the model. This version 2 finetune should be much better than version 1 in terms of speaker similarity, naturalism, and pronunciation.
📝 Dataset
Length: 152.79 hours
Audio samples: 69656
Dataset sources:
• Indonesian Youtube videos, cutted and preprocessed, samples voice
🔎 License
The pre-trained model is licensed under the CC-BY-NC license due to the training data Emilia, which is an in-the-wild dataset and the finetune data which is also an in-the-wild dataset. Sorry for any inconvenience this may cause.
Model tree for dev-rexpro/masbro-f5-tts
Base model
SWivid/F5-TTS