Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- Levantine Arabic
|
4 |
+
- Shami
|
5 |
+
- English
|
6 |
+
---
|
7 |
+
|
8 |
+
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
# English2Dialect
|
13 |
+
|
14 |
+
This model generates translations from English to colloquial Arabic, conditioning the translations on dialect. Supported dialects are: Palestinian/Jordanian, Syrian, Lebanese and Egyptian.
|
15 |
+
Dialect is specified via the first input token which should be either P/S/L/E.
|
16 |
+
|
17 |
+
For example, to translate to Palestinian/Jordanian, use the input:
|
18 |
+
|
19 |
+
`P What time is it now?`
|
20 |
+
|
21 |
+
And for Syrian:
|
22 |
+
|
23 |
+
`S What time is it now?`
|
24 |
+
|
25 |
+
- **Demo:** https://huggingface.co/spaces/guymorlan/English2Shami
|
26 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
27 |
+
|
28 |
+
## Training Data
|
29 |
+
The model was trained by fine-tuning the opus-mt-ar-en (MSA to English) model on ~85K parallel sentences in four dialects of colloquial Arabic.
|
30 |
+
|
31 |
+
## Model Description
|
32 |
+
|
33 |
+
<!-- Provide a longer summary of what this model is. -->
|
34 |
+
|
35 |
+
- **Developed by:** Guy Mor-Lan (guy.mor@mail.huji.ac.il)
|
36 |
+
- **Model type:** MarianMT Seq2Seq
|
37 |
+
- **License:** MIT
|
38 |
+
- **Finetuned from model:** Helsinki-NLP/opus-mt-ar-en[https://huggingface.co/Helsinki-NLP/opus-mt-ar-en]
|
39 |
+
|
40 |
+
<!--- **Repository:** [More Information Needed] -->
|