README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: afl-3.0
|
| 3 |
+
language:
|
| 4 |
+
- 'no'
|
| 5 |
+
base_model:
|
| 6 |
+
- SWivid/F5-TTS
|
| 7 |
+
pipeline_tag: text-to-speech
|
| 8 |
+
---
|
| 9 |
+
# Model Card for akhbar/F5_Norwegian
|
| 10 |
+
|
| 11 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 12 |
+
|
| 13 |
+
This is a Norwegian Text2Speech model based on SWivid/F5-TTS.
|
| 14 |
+
The model was trained from scratch on a custom built dataset based on various datasets from the [National Library of Norway.] (https://www.nb.no/sprakbanken/en/resource-catalogue/?_type=speech)
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
The mode was trained from scratch with the F5Base architecture.
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
- **Developed by:** Akhbar
|
| 23 |
+
- **Model type:** Text To Speach (TTS)
|
| 24 |
+
- **Language(s) (NLP):** Norwegian
|
| 25 |
+
- **License:** AFL-3.0
|
| 26 |
+
|
| 27 |
+
### Model Sources
|
| 28 |
+
|
| 29 |
+
<!-- Provide the basic links for the model. -->
|
| 30 |
+
|
| 31 |
+
- **Repository:** https://github.com/SWivid/F5-TTS
|
| 32 |
+
- **Paper:** F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (https://arxiv.org/abs/2410.06885)
|