Token Classification
Transformers
ONNX
Safetensors
Danish
electra
punctuation-restoration
sentence-boundary-detection
truecasing
danish
Instructions to use RyeAI/ekko-pnc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RyeAI/ekko-pnc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="RyeAI/ekko-pnc")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("RyeAI/ekko-pnc") model = AutoModelForTokenClassification.from_pretrained("RyeAI/ekko-pnc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
List PnC as CC BY 4.0 with CoRal terms disclosed
Browse files
README.md
CHANGED
|
@@ -1,8 +1,7 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- da
|
| 4 |
-
license:
|
| 5 |
-
license_name: cc-by-4.0-plus-coral-adapted-material
|
| 6 |
license_link: https://huggingface.co/RyeAI/ekko-pnc/blob/d8ea368b1c442efdfea83aa0ac2d35e7715395ee/MODEL_LICENSE.md
|
| 7 |
library_name: transformers
|
| 8 |
pipeline_tag: token-classification
|
|
@@ -108,9 +107,10 @@ above uses human-reviewed punctuation instead.
|
|
| 108 |
|
| 109 |
## License and data terms
|
| 110 |
|
| 111 |
-
|
|
|
|
| 112 |
[`LICENSES/`](LICENSES/) for the terms and source notices. CoRal restrictions
|
| 113 |
-
apply to this model
|
| 114 |
its data as CC0 1.0; its legal text is included here. FT Speech's source statement
|
| 115 |
and the two Folketinget terms it names are linked in the license bundle. The
|
| 116 |
effect of those terms on redistributed weights is not settled by this card.
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- da
|
| 4 |
+
license: cc-by-4.0
|
|
|
|
| 5 |
license_link: https://huggingface.co/RyeAI/ekko-pnc/blob/d8ea368b1c442efdfea83aa0ac2d35e7715395ee/MODEL_LICENSE.md
|
| 6 |
library_name: transformers
|
| 7 |
pipeline_tag: token-classification
|
|
|
|
| 107 |
|
| 108 |
## License and data terms
|
| 109 |
|
| 110 |
+
Ekko PnC v2 is released under CC BY 4.0. See
|
| 111 |
+
[`MODEL_LICENSE.md`](MODEL_LICENSE.md), [`NOTICE`](NOTICE), and
|
| 112 |
[`LICENSES/`](LICENSES/) for the terms and source notices. CoRal restrictions
|
| 113 |
+
also apply to this model. The NST-da dataset card identifies
|
| 114 |
its data as CC0 1.0; its legal text is included here. FT Speech's source statement
|
| 115 |
and the two Folketinget terms it names are linked in the license bundle. The
|
| 116 |
effect of those terms on redistributed weights is not settled by this card.
|