ithuan/f5-tts-formosan-all-finetune-v3

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

Model Details

F5-TTS finetune on all formosan data (ithuan, fb ilrdf dict, klokah) without samples only one word or no translation, using ipa as input.
g2p from this repo.

Training Details

• learning rate: 0.00001
• batch size per gpu: 15127
• batch size type: frame
• max samples: 64
• grad accumulation steps: 1
• max grad norm: 1
• epochs: 253
• num warmup updates: 20886

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/ithuan/formosan-f5-tts