Commit
·
c704d3d
1
Parent(s):
f7788b6
Update README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# bart-translation-zh-yue
|
16 |
|
17 |
-
This model is a fine-tuned version of [indiejoseph/bart-base-cantonese](https://huggingface.co/indiejoseph/bart-base-cantonese) on the
|
|
|
18 |
It achieves the following results on the evaluation set:
|
19 |
- Loss: 0.5042
|
20 |
- Bleu: 36.3458
|
@@ -30,7 +31,9 @@ More information needed
|
|
30 |
|
31 |
## Training and evaluation data
|
32 |
|
33 |
-
|
|
|
|
|
34 |
|
35 |
## Training procedure
|
36 |
|
|
|
14 |
|
15 |
# bart-translation-zh-yue
|
16 |
|
17 |
+
This model is a fine-tuned version of [indiejoseph/bart-base-cantonese](https://huggingface.co/indiejoseph/bart-base-cantonese) on the LLMs generated dataset.
|
18 |
+
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.5042
|
21 |
- Bleu: 36.3458
|
|
|
31 |
|
32 |
## Training and evaluation data
|
33 |
|
34 |
+
The training and evaludation dataset are generated by ChatGPT and Palm2.
|
35 |
+
|
36 |
+
Leverage over 4,000 Chinese and Cantonese phrase pairs meticulously gathered from diverse websites and dictionaries as the foundation for generating initial seed sentences in Chinese using ChatGPT. Subsequently, employ the Palm2 API to translate all Chinese sentences into Cantonese, while dedicating attention to manually rectifying any typos and enhancing overall fluency and linguistic variety.
|
37 |
|
38 |
## Training procedure
|
39 |
|