openslr added to README
Browse files
README.md
CHANGED
|
@@ -15,13 +15,14 @@ tags:
|
|
| 15 |
|
| 16 |
datasets:
|
| 17 |
- mozilla-foundation/common_voice_8_0
|
|
|
|
| 18 |
|
| 19 |
---
|
| 20 |
|
| 21 |
# Aina Project's Catalan multi-speaker text-to-speech model
|
| 22 |
## Model description
|
| 23 |
|
| 24 |
-
This model was trained from scratch using the [Coqui TTS](https://github.com/coqui-ai/TTS) toolkit on a combination of 3 datasets: [Festcat](http://festcat.talp.cat/devel.php), high quality open speech dataset of [Google](http://openslr.org/69/) and [Common Voice v8](https://commonvoice.mozilla.org/ca). For the training, 101460 utterances consisting of 257 speakers were used, which corresponds to nearly 138 hours of speech.
|
| 25 |
|
| 26 |
A live inference demo can be found in our spaces, [here](https://huggingface.co/spaces/projecte-aina/tts-ca-coqui-vits-multispeaker).
|
| 27 |
|
|
|
|
| 15 |
|
| 16 |
datasets:
|
| 17 |
- mozilla-foundation/common_voice_8_0
|
| 18 |
+
- openslr
|
| 19 |
|
| 20 |
---
|
| 21 |
|
| 22 |
# Aina Project's Catalan multi-speaker text-to-speech model
|
| 23 |
## Model description
|
| 24 |
|
| 25 |
+
This model was trained from scratch using the [Coqui TTS](https://github.com/coqui-ai/TTS) toolkit on a combination of 3 datasets: [Festcat](http://festcat.talp.cat/devel.php), high quality open speech dataset of [Google](http://openslr.org/69/) (can be found in [OpenSLR 69](https://huggingface.co/datasets/openslr/viewer/SLR69/train)) and [Common Voice v8](https://commonvoice.mozilla.org/ca). For the training, 101460 utterances consisting of 257 speakers were used, which corresponds to nearly 138 hours of speech.
|
| 26 |
|
| 27 |
A live inference demo can be found in our spaces, [here](https://huggingface.co/spaces/projecte-aina/tts-ca-coqui-vits-multispeaker).
|
| 28 |
|