Update README.md
#2
by
prajdabre
- opened
README.md
CHANGED
@@ -27,7 +27,7 @@ pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")
|
|
27 |
# The following language indicator tokens are usable: <2acf>, <2aoa>, <2ara>, <2aze>, <2bah>, <2brc>, <2bzj>, <2bzk>, <2cab>, <2ceb>, <2cri>, <2crs>, <2dcr>, <2deu>, <2djk>, <2eng>, <2fab>, <2fng>, <2fpe>, <2fra>, <2gcf>, <2gcr>, <2gpe>, <2gul>, <2gyn>, <2hat>, <2icr>, <2jam>, <2kea>, <2kri>, <2ktu>, <2lou>, <2mart1259>, <2mfe>, <2mue>, <2nep>, <2pap>, <2pcm>, <2por>, <2pov>, <2pre>, <2rcf>, <2sag>, <2spa>, <2srm>, <2srn>, <2svc>, <2tpi>, <2trf>, <2wes>, <2zho>
|
28 |
# For what language each language code corresponds to please look here: https://github.com/JHU-CLSP/Kreyol-MT?tab=readme-ov-file#building-machine-translation-for-latin-american-caribbean-and-colonial-african-creole-languages
|
29 |
|
30 |
-
inp = tokenizer('
|
31 |
|
32 |
model.eval() # Set dropouts to zero
|
33 |
|
|
|
27 |
# The following language indicator tokens are usable: <2acf>, <2aoa>, <2ara>, <2aze>, <2bah>, <2brc>, <2bzj>, <2bzk>, <2cab>, <2ceb>, <2cri>, <2crs>, <2dcr>, <2deu>, <2djk>, <2eng>, <2fab>, <2fng>, <2fpe>, <2fra>, <2gcf>, <2gcr>, <2gpe>, <2gul>, <2gyn>, <2hat>, <2icr>, <2jam>, <2kea>, <2kri>, <2ktu>, <2lou>, <2mart1259>, <2mfe>, <2mue>, <2nep>, <2pap>, <2pcm>, <2por>, <2pov>, <2pre>, <2rcf>, <2sag>, <2spa>, <2srm>, <2srn>, <2svc>, <2tpi>, <2trf>, <2wes>, <2zho>
|
28 |
# For what language each language code corresponds to please look here: https://github.com/JHU-CLSP/Kreyol-MT?tab=readme-ov-file#building-machine-translation-for-latin-american-caribbean-and-colonial-african-creole-languages
|
29 |
|
30 |
+
inp = tokenizer('Mi tingk se yu de tel mi lai. </s> <2jam>', add_special_tokens=False, return_tensors="pt", padding=True).input_ids
|
31 |
|
32 |
model.eval() # Set dropouts to zero
|
33 |
|