jayparks/tf-seq2seq
Sequence to sequence learning using TensorFlow.
This project helps researchers and practitioners in natural language processing (NLP) to build and train machine translation models. It takes parallel text data in two languages as input, preprocesses it, and then outputs a trained model that can translate text from one language to another. The ideal user is someone working on language translation, summarization, or other sequence-to-sequence tasks.
389 stars. No commits in the last 6 months.
Use this if you need to create a custom machine translation system or experiment with different neural network architectures for sequence-to-sequence tasks.
Not ideal if you're looking for a pre-trained, ready-to-use translation API or a solution for tasks outside of sequence generation.
Stars
389
Forks
108
Language
Python
License
—
Category
Last pushed
Apr 16, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jayparks/tf-seq2seq"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...
awslabs/sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
OpenNMT/OpenNMT-tf
Neural machine translation and sequence learning using TensorFlow