Update README.md
Browse files
README.md
CHANGED
|
@@ -18,10 +18,6 @@ tags:
|
|
| 18 |
|
| 19 |
Hugin is a small, fast Swedish text-to-speech model that also reads English, both on its own and mixed into Swedish sentences. It is a 15 M parameter non-autoregressive Transformer (phonemes -> durations -> mel in one pass, no sampling, no diffusion) with an 8 M parameter Vocos vocoder, and outputs 24 kHz audio. It ships with one voice, **B1** (`w`), a synthetic voice designed with VoxCPM2, and with **`hugin-finetune`**, which makes your own voice from about 500 recorded sentences. The text front-end handles numbers, dates, abbreviations, acronyms, homographs, word stress and English detection. The packaged version is v0.8-en.
|
| 20 |
|
| 21 |
-
<video controls preload="none" width="100%" poster="https://huggingface.co/codah80/futhark-hugin/resolve/main/media/futhark_showreel_poster.jpg" src="https://huggingface.co/codah80/futhark-hugin/resolve/main/media/futhark_showreel.mp4"></video>
|
| 22 |
-
|
| 23 |
-
*The Futhark family in 70 seconds: Hugin (this model) and the larger Munin and Sleipner models (not included in this repository). All speech is generated by the models.*
|
| 24 |
-
|
| 25 |
## Listen
|
| 26 |
|
| 27 |
Generated with this package on CPU, voice B1, no editing.
|
|
|
|
| 18 |
|
| 19 |
Hugin is a small, fast Swedish text-to-speech model that also reads English, both on its own and mixed into Swedish sentences. It is a 15 M parameter non-autoregressive Transformer (phonemes -> durations -> mel in one pass, no sampling, no diffusion) with an 8 M parameter Vocos vocoder, and outputs 24 kHz audio. It ships with one voice, **B1** (`w`), a synthetic voice designed with VoxCPM2, and with **`hugin-finetune`**, which makes your own voice from about 500 recorded sentences. The text front-end handles numbers, dates, abbreviations, acronyms, homographs, word stress and English detection. The packaged version is v0.8-en.
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## Listen
|
| 22 |
|
| 23 |
Generated with this package on CPU, voice B1, no editing.
|