Instructions to use techiaith/fullstop-welsh-punctuation-prediction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use techiaith/fullstop-welsh-punctuation-prediction with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="techiaith/fullstop-welsh-punctuation-prediction")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("techiaith/fullstop-welsh-punctuation-prediction") model = AutoModelForTokenClassification.from_pretrained("techiaith/fullstop-welsh-punctuation-prediction", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Language Technologies, Bangor University commited on
Commit ·
6d7256e
1
Parent(s): 228eb07
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ metrics:
|
|
| 16 |
|
| 17 |
This model predicts the punctuation of Welsh language texts. It has been created to restore punctuation of transcribed from speech recognition models such as https://huggingface.co/techiaith/wav2vec2-xlsr-ft-cy. The model restores the following punctuation markers: "." "," "?" "-" ":"
|
| 18 |
|
| 19 |
-
The model was trained on Welsh texts extracted from the Welsh Parliament / Senedd
|
| 20 |
|
| 21 |
Based on the work of https://github.com/oliverguhr/fullstop-deep-punctuation-prediction and [softcatala/fullstop-catalan-punctuation-prediction](https://huggingface.co/softcatala/fullstop-catalan-punctuation-prediction)
|
| 22 |
|
|
|
|
| 16 |
|
| 17 |
This model predicts the punctuation of Welsh language texts. It has been created to restore punctuation of transcribed from speech recognition models such as https://huggingface.co/techiaith/wav2vec2-xlsr-ft-cy. The model restores the following punctuation markers: "." "," "?" "-" ":"
|
| 18 |
|
| 19 |
+
The model was trained on Welsh texts extracted from the Welsh Parliament / Senedd Record of Proceedings between 1999-2010 and 2016 to the present day. Please note that the training data consists of originally spoken and translated political speeches. Therefore the model might perform differently on texts from other domains.
|
| 20 |
|
| 21 |
Based on the work of https://github.com/oliverguhr/fullstop-deep-punctuation-prediction and [softcatala/fullstop-catalan-punctuation-prediction](https://huggingface.co/softcatala/fullstop-catalan-punctuation-prediction)
|
| 22 |
|