Update README.md
Browse files
README.md
CHANGED
@@ -34,7 +34,7 @@ Translate a sentence using python
|
|
34 |
import ctranslate2
|
35 |
import pyonmttok
|
36 |
from huggingface_hub import snapshot_download
|
37 |
-
model_dir = snapshot_download(repo_id="projecte-aina/
|
38 |
|
39 |
tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/spm.model")
|
40 |
tokenized=tokenizer.tokenize("Benvingut al projecte Aina!")
|
@@ -125,7 +125,7 @@ We use the BLEU score for evaluation on the [Flores-101](https://github.com/face
|
|
125 |
Below are the evaluation results on the machine translation from Catalan to Portuguese
|
126 |
compared to [Softcatalà](https://www.softcatala.org/) and [Google Translate](https://translate.google.es/?hl=es):
|
127 |
|
128 |
-
| Test set | SoftCatalà | Google Translate |
|
129 |
|----------------------|------------|------------------|---------------|
|
130 |
| Flores 101 dev | 30,9 | **41,4** | 34,3 |
|
131 |
| Flores 101 devtest |31,6 | **41,3** | 35,2 |
|
|
|
34 |
import ctranslate2
|
35 |
import pyonmttok
|
36 |
from huggingface_hub import snapshot_download
|
37 |
+
model_dir = snapshot_download(repo_id="projecte-aina/aina-translator-ca-pt", revision="main")
|
38 |
|
39 |
tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/spm.model")
|
40 |
tokenized=tokenizer.tokenize("Benvingut al projecte Aina!")
|
|
|
125 |
Below are the evaluation results on the machine translation from Catalan to Portuguese
|
126 |
compared to [Softcatalà](https://www.softcatala.org/) and [Google Translate](https://translate.google.es/?hl=es):
|
127 |
|
128 |
+
| Test set | SoftCatalà | Google Translate | aina-translator-ca-pt |
|
129 |
|----------------------|------------|------------------|---------------|
|
130 |
| Flores 101 dev | 30,9 | **41,4** | 34,3 |
|
131 |
| Flores 101 devtest |31,6 | **41,3** | 35,2 |
|