Instructions to use Mavkif/m2m100_rup_tokenizer_both with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mavkif/m2m100_rup_tokenizer_both with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Mavkif/m2m100_rup_tokenizer_both", dtype="auto", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Muhammad Umer Tariq Butt commited on
Commit ·
60692f8
1
Parent(s): 7fa4edc
updated readme
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ These tokens are stored in `added_tokens.json` and are required for correct tran
|
|
| 25 |
|
| 26 |
---
|
| 27 |
|
| 28 |
-
When preparing input for models, prepend the correct language token (__roman-ur__ or __ur__) to the text.
|
| 29 |
|
| 30 |
@inproceedings{butt2025romanurdu,
|
| 31 |
title = {Low-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models},
|
|
|
|
| 25 |
|
| 26 |
---
|
| 27 |
|
| 28 |
+
When preparing input for models, prepend the correct language token (`__roman-ur__` or `__ur__`) to the text.
|
| 29 |
|
| 30 |
@inproceedings{butt2025romanurdu,
|
| 31 |
title = {Low-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models},
|