Update README.md
Browse files
README.md
CHANGED
|
@@ -36,7 +36,9 @@ model-index:
|
|
| 36 |
# Aina Project's Catalan text-to-speech model
|
| 37 |
## Model description
|
| 38 |
|
| 39 |
-
This model was fine-tuned from a pre-trained Spanish [stt-es-citrinet-512](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_es_citrinet_512) model using the [NeMo](https://github.com/NVIDIA/NeMo) toolkit.
|
|
|
|
|
|
|
| 40 |
|
| 41 |
## Intended uses and limitations
|
| 42 |
|
|
|
|
| 36 |
# Aina Project's Catalan text-to-speech model
|
| 37 |
## Model description
|
| 38 |
|
| 39 |
+
This model transcribes audio samples in Catalan to lowercase text without punctuation. The model was fine-tuned from a pre-trained Spanish [stt-es-citrinet-512](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_es_citrinet_512) model using the [NeMo](https://github.com/NVIDIA/NeMo) toolkit. The model has around 36.5M parámeters.
|
| 40 |
+
|
| 41 |
+
The model has been trained on [Common Voice 11.0](https://commonvoice.mozilla.org/en/datasets).
|
| 42 |
|
| 43 |
## Intended uses and limitations
|
| 44 |
|