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
Document validated hardware support
Browse files
README.md
CHANGED
|
@@ -75,6 +75,12 @@ held-out PnC manifest:
|
|
| 75 |
|
| 76 |
The small quantization delta is why int8 is the default local artifact.
|
| 77 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
## Limitations
|
| 79 |
|
| 80 |
- Danish only; restores commas, periods, question marks, exclamation marks, and
|
|
|
|
| 75 |
|
| 76 |
The small quantization delta is why int8 is the default local artifact.
|
| 77 |
|
| 78 |
+
## Validated hardware
|
| 79 |
+
|
| 80 |
+
Both ONNX exports passed on Linux x64 CPU, and the int8 export passed as part of
|
| 81 |
+
the macOS arm64 Tiny runtime smoke. Windows x64 and physical iOS/Android device
|
| 82 |
+
validation remain pending. PnC does not require a GPU.
|
| 83 |
+
|
| 84 |
## Limitations
|
| 85 |
|
| 86 |
- Danish only; restores commas, periods, question marks, exclamation marks, and
|