Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-4.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-4.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
This vits model was trained on the [KTH/hungarian-single-speaker-tts](https://huggingface.co/datasets/KTH/hungarian-single-speaker-tts) dataset.
|
| 6 |
+
|
| 7 |
+
## CSS10 Hungarian: Single Speaker Speech Dataset
|
| 8 |
+
The corpus consists of a single speaker, with 4515 segments extracted from [this](https://librivox.org/egri-csillagok-by-geza-gardonyi/) single LibriVox audiobook. It consists about 10 hours of audio data.
|
| 9 |
+
|
| 10 |
+
## Training
|
| 11 |
+
The model was trained on a single RTX 3090 GPU. The training took about 3 days.
|
| 12 |
+
|
| 13 |
+
We created a Hungarian text cleaner function for this dataset, which can be found in the `text/cleaners.py` file.
|