Instructions to use CadenzaBaron/M2M100-418M-for-GameTranslation-Finetuned-Zh-En with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CadenzaBaron/M2M100-418M-for-GameTranslation-Finetuned-Zh-En with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="CadenzaBaron/M2M100-418M-for-GameTranslation-Finetuned-Zh-En")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("CadenzaBaron/M2M100-418M-for-GameTranslation-Finetuned-Zh-En") model = AutoModelForSeq2SeqLM.from_pretrained("CadenzaBaron/M2M100-418M-for-GameTranslation-Finetuned-Zh-En") - Notebooks
- Google Colab
- Kaggle
Commit ·
ded9b9b
1
Parent(s): ed5f209
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,11 @@ metrics:
|
|
| 16 |
|
| 17 |
This is a finetuned version of Facebook/M2M100.
|
| 18 |
It has been trained on a parallel corpus on several Chinese video games translations. All of them are from human/fan translations.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
Sample generation script :
|
| 21 |
|
|
|
|
| 16 |
|
| 17 |
This is a finetuned version of Facebook/M2M100.
|
| 18 |
It has been trained on a parallel corpus on several Chinese video games translations. All of them are from human/fan translations.
|
| 19 |
+
It's not perfect but it's the best I could do. It should be sitting somewhere between Google Translate and DeepL, I guess.
|
| 20 |
+
But it has upsides for first MT pass in a game translation context :
|
| 21 |
+
1) It should not mess up tags
|
| 22 |
+
2) It has basic cultivation/martial arts vocabulary
|
| 23 |
+
3) Nothing is locked behind a paywall \o/
|
| 24 |
|
| 25 |
Sample generation script :
|
| 26 |
|