Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# opus-mt-cantonese-v2
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh)
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 1.8948
|
| 21 |
- Bleu: 4.1931
|
|
@@ -23,18 +23,22 @@ It achieves the following results on the evaluation set:
|
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
## Intended uses & limitations
|
| 29 |
|
| 30 |
-
|
| 31 |
|
| 32 |
## Training and evaluation data
|
| 33 |
|
| 34 |
-
|
|
|
|
|
|
|
| 35 |
|
| 36 |
## Training procedure
|
| 37 |
|
|
|
|
|
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
|
|
|
| 15 |
|
| 16 |
# opus-mt-cantonese-v2
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh).
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 1.8948
|
| 21 |
- Bleu: 4.1931
|
|
|
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
| 26 |
+
This model translates English into Cantonese.
|
| 27 |
|
| 28 |
## Intended uses & limitations
|
| 29 |
|
| 30 |
+
Translations produced are for experimental purposes. Correctness is not guaranteed. Use at your own risk.
|
| 31 |
|
| 32 |
## Training and evaluation data
|
| 33 |
|
| 34 |
+
Trained with Cantonese sentences with English translations:
|
| 35 |
+
- 6280 from Tatoeba.
|
| 36 |
+
- 1232 from CantoDict.
|
| 37 |
|
| 38 |
## Training procedure
|
| 39 |
|
| 40 |
+
80% training / 20% validation. 20 epochs.
|
| 41 |
+
|
| 42 |
### Training hyperparameters
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|