awslabs/sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
This is a neural machine translation framework designed for researchers and developers working with language models. It takes large datasets of text in one language and corresponding translations in another, then trains a model to translate new text between those languages. The output is a high-quality machine translation model that can power applications like automated translation services.
1,217 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to build and train your own custom neural machine translation models for specific language pairs or domains.
Not ideal if you are looking for a ready-to-use translation tool without needing to train custom models, or if you prefer a non-developer-centric solution.
Stars
1,217
Forks
320
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 24, 2024
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/awslabs/sockeye"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
facebookresearch/fairseq2
FAIR Sequence Modeling Toolkit 2
lhotse-speech/lhotse
Tools for handling multimodal data in machine learning projects.
google/sequence-layers
A neural network layer API and library for sequence modeling, designed for easy creation of...
OpenNMT/OpenNMT-tf
Neural machine translation and sequence learning using TensorFlow
mozilla/translations
The code, training pipeline, and models that power Firefox Translations