Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,33 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-nc-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- mozilla-foundation/common_voice_17_0
|
| 5 |
+
language:
|
| 6 |
+
- tr
|
| 7 |
+
base_model:
|
| 8 |
+
- SWivid/F5-TTS
|
| 9 |
+
pipeline_tag: text-to-speech
|
| 10 |
+
tags:
|
| 11 |
+
- audio
|
| 12 |
+
- tts
|
| 13 |
+
- turkish
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
Inference with .safetensors option
|
| 18 |
+
```
|
| 19 |
+
f5_tts_turkish_650000.safetensors
|
| 20 |
+
vocab.txt
|
| 21 |
+
```
|
| 22 |
+
Github: https://github.com/SWivid/F5-TTS
|
| 23 |
+
Paper: [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://huggingface.co/papers/2410.06885)
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
## Samples
|
| 27 |
+
|
| 28 |
+
Ref: https://voca.ro/1fxdnqkzN4wR
|
| 29 |
+
Gen: https://voca.ro/1nM46muVinRS
|
| 30 |
+
|
| 31 |
+
> **_NOTE:_** You can set the number of nfe steps to 64 to produce better quality sound.
|
| 32 |
+
|
| 33 |
+
> **_NOTE:_** Finetuning is in progress!
|