formospeech/f5-tts-hita-finetune-v1

Model Card for f5-tts-hakka-finetune-v3

Model Details

F5-TTS finetune on Taiwanese Hakka for TTS without word dataset and samples have in hanzi, using pinyin as input.
g2p from this repo.

Training Details

• learning rate: 0.00001
• batch size per gpu: 20169
• batch size type: frame
• max samples: 64
• grad accumulation steps: 1
• max grad norm: 1
• epochs: 861 (incomplete)
• num warmup updates: 13362

Model Sources

• Repository: https://github.com/SWivid/F5-TTS
• Paper: https://arxiv.org/abs/2410.06885

Uses

please refer source repo

Demo

https://huggingface.co/spaces/formospeech/taiwanese-hakka-f5-tts