Text-to-Speech
F5-TTS
Italian
f5-ita-test / README.md
alien79's picture
Update README.md
5c7f270 verified
|
raw
history blame
507 Bytes
metadata
datasets:
  - facebook/multilingual_librispeech
language:
  - it
base_model:
  - SWivid/F5-TTS
pipeline_tag: text-to-speech
license: cc-by-4.0

This is a test to see how to finetune F5 in italian

Trained over 247+h hours of "train" split of facebook/multilingual_librispeech dataset, 6700 steps for Epoch:

  • catastrophic failure (the model forgot english)
  • italian pronunciation not perfect

The run.py file is an example of how to extract the wav files and produce the metadata.csv to use for training