Instructions to use cfinley/punct_restore_fr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cfinley/punct_restore_fr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="cfinley/punct_restore_fr")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("cfinley/punct_restore_fr") model = AutoModelForTokenClassification.from_pretrained("cfinley/punct_restore_fr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download predict_results.json from cfinley/punct_restore_fr: direct link, hf CLI and curl.
- Browser
- Download file 326 Bytes
-
https://huggingface.co/cfinley/punct_restore_fr/resolve/main/predict_results.json
- Command line
-
hf download hf://cfinley/punct_restore_fr/predict_results.json
-
curl -L -o predict_results.json https://huggingface.co/cfinley/punct_restore_fr/resolve/main/predict_results.json
326 Bytes
| { | |
| "predict_accuracy": 0.9907505424296343, | |
| "predict_f1": 0.952959144711722, | |
| "predict_loss": 0.03142160549759865, | |
| "predict_precision": 0.9562085743841232, | |
| "predict_recall": 0.9497317249514822, | |
| "predict_runtime": 31.6681, | |
| "predict_samples_per_second": 131.457, | |
| "predict_steps_per_second": 16.452 | |
| } |