Initial commit

README.md

@@ -1,14 +1,13 @@
 ---
 language:
 - ar
+- ca
 - es
 - fr
+- gl
 - it
-- itc
-- la
-
-language_bcp47:
-- la_Latn
+- pt
+- ro
 
 tags:
 - translation
@@ -177,8 +176,10 @@ This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus
 - **Release**: 2022-08-09
 - **License:** CC-BY-4.0
 - **Language(s):**  
-  - Source Language(s): fra ita lat_Latn spa
+  - Source Language(s): cat fra glg ita lat_Latn por ron spa
   - Target Language(s): ara
+  - Language Pair(s): cat-ara fra-ara glg-ara ita-ara por-ara ron-ara spa-ara
+  - Valid Target Language Labels: >>ajp<< >>apc<< >>ara<< >>arq<< >>ary<< >>arz<<
 - **Original Model**: [opusTCv20210807_transformer-big_2022-08-09.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-ara/opusTCv20210807_transformer-big_2022-08-09.zip)
 - **Resources for more information:**
   - [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
@@ -186,6 +187,8 @@ This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus
   - [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
   - [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/
 
+This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>ara<<`
+
 ## Uses
 
 This model can be used for translation and text-to-text generation.
@@ -297,5 +300,5 @@ The work is supported by the [European Language Grid](https://www.european-langu
 
 * transformers version: 4.16.2
 * OPUS-MT git hash: 8b9f0b0
-* port time: Fri Aug 12 14:32:03 EEST 2022
+* port time: Sat Aug 13 00:00:31 EEST 2022
 * port machine: LM0-400-22516.local