Text-to-Speech
Finnish
AsmoKoskinen's picture
Update README.md
df0d630 verified
|
raw
history blame
405 Bytes
metadata
license: cc-by-nc-4.0
datasets:
  - mozilla-foundation/common_voice_17_0
  - facebook/voxpopuli
language:
  - fi
base_model:
  - SWivid/F5-TTS

This is F5-TTS Finnish Model. Based on Common Voice and Vox Populi Finnish Datasets.

  • Epochs: 200

  • Speakers: Multiple speakers from different corpus

Can't understand numbers, turn numbers into words.

This is first round, the work of development continues.