Instructions to use kz/mt5base-finetuned-ECC-japanese-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kz/mt5base-finetuned-ECC-japanese-small with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("kz/mt5base-finetuned-ECC-japanese-small") model = AutoModelForSeq2SeqLM.from_pretrained("kz/mt5base-finetuned-ECC-japanese-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: "ja"
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
Google's mt5-base fine-tuned in Japanese to solve error detection and correction.
|
| 6 |
+
|
| 7 |
+
#日本語誤り訂正
|
| 8 |
+
|
| 9 |
+
- "吾輩をは猫である。名前えはまだない。"→"吾輩は猫である。名前はまだない。"
|
| 10 |
+
|
| 11 |
+
- "-small" has been trained on 20,000 text pairs.
|
| 12 |
+
- prefix: "correction: " (notice: single task trained.)
|
| 13 |
+
|
| 14 |
+
**check in progress**
|
| 15 |
+
|