Comments (5)
Thanks for quick response. I need to use the format f'>>pt_BR<< {text}' for both models.
from easynmt.
Hi @jubs12
Thanks for pointing this out to me. As there are so many opus-mt models, I was not able to check them all :)
The ROMANCE model supports several languages:
fr,fr_BE,fr_CA,fr_FR,wa,frp,oc,ca,rm,lld,fur,lij,lmo,es,es_AR,es_CL,es_CO,es_CR,es_DO,es_EC,es_ES,es_GT,es_HN,es_MX,es_NI,es_PA,es_PE,es_PR,es_SV,es_UY,es_VE,pt,pt_br,pt_BR,pt_PT,gl,lad,an,mwl,it,it_IT,co,nap,scn,vec,sc,ro,la
Do you know if you have to somehow specific which language your source language is? Or does it work for any of these languages without providing encoding the source language.
For the model en-ROMANCE, you have to provide as token the target language. So there I have to figure it out what a good way would be to include these multi-lingual opus-mt models.
from easynmt.
great, that is helpful.
from easynmt.
@nreimers any update on supporting these ROMANCE languages in EasyNMT? Alternatively, is there any guide on how to deploy this Opus MT Romance model in a standalone fashion? We have a need for Brazilian Portuguese translation which seems to be supported by this model. Thanks!
from easynmt.
@nreimers any update on supporting these ROMANCE languages in EasyNMT? Alternatively, is there any guide on how to deploy this Opus MT Romance model in a standalone fashion? We have a need for Brazilian Portuguese translation which seems to be supported by this model. Thanks!
I figured out how to send the language tokens as per the instructions from https://huggingface.co/Helsinki-NLP/opus-mt-en-ROMANCE and comments from @jubs12 above.
So specifying ROMANCE
as the target language code, along with this works for me since I use EasyNMT as a translation server. Sample EasyNMT GET request URL path for language code pt_br
(Brazilian Portuguese):
/translate?target_lang=ROMANCE&text=%3E%3Ept_br%3C%3CMoscow&source_lang=en&beam_size=2
from easynmt.
Related Issues (20)
- some questions HOT 4
- Model with Docker Image HOT 1
- i suggest you add the tatoeba challenge models.
- cpu bottleneck : tokenization with a single worker HOT 2
- [ERROR] Exception in ASGI application HOT 1
- Onnx conversion HOT 2
- Question about OSError: Helsinki-NLP/opus-mt-fa-en is not a local folder HOT 1
- Local/offline use of additional Opus-MT models
- MBart50Converter requires the protobuf library but it was not found in your environment. HOT 2
- Do not translate word HOT 3
- (Big) transformer Tatoeba models
- Maybe http3 related bug or not? HOT 1
- Support for NLLB HOT 5
- Enable manually specifying the desired OPUS model? HOT 3
- Exception when trying to download Response 403 HOT 5
- Workflow for large datasets
- How to run test_translation_speed.py HOT 2
- EasyNMT
- Is there randomness in translation or does every translation lead to the exact same output?
- Finetune/Train on custom dataset
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from easynmt.