---
license: cc-by-nc-4.0
datasets:
- amphion/Emilia-Dataset
language:
- hu
base_model:
- SWivid/F5-TTS
pipeline_tag: text-to-speech
---
### 2024/10/23 Version 1.1 Reduce checkpoint size 5.4->1.4 GByte
### 2024/10/22 Version 1.0 of the fine-tuned model has been uploaded. 122,000 steps
Datasets:
- https://www.kaggle.com/datasets/bryanpark/hungarian-single-speaker-speech-dataset

Github: https://github.com/SWivid/F5-TTS      
Paper: [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://huggingface.co/papers/2410.06885)