https://github.com/etcetra7n/en-fr-translator
Implementation of the original transformer model described by Vaswani et al for English to German translation
https://github.com/etcetra7n/en-fr-translator
ai attention-is-all-you-need attention-mechanism machine-learning python transformers translator
Last synced: 7 months ago
JSON representation
Implementation of the original transformer model described by Vaswani et al for English to German translation
- Host: GitHub
- URL: https://github.com/etcetra7n/en-fr-translator
- Owner: etcetra7n
- Created: 2024-06-24T12:37:15.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-06-24T16:06:49.000Z (over 1 year ago)
- Last Synced: 2025-02-02T07:13:23.486Z (8 months ago)
- Topics: ai, attention-is-all-you-need, attention-mechanism, machine-learning, python, transformers, translator
- Language: Jupyter Notebook
- Homepage:
- Size: 3.6 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# English to German Translator
This is the implementation of the original transformer model described by Vaswani et al in the
paper "Attention is all you need", implemented using tensorflow and keras. It is trained on a
small dataset consisting of about 150000 English to German sentence pairs. It features all the
elements described in the paper including Mulltihead Attention mechanism, Positional Encoding and
a learning rate scheduler. However due to limitations of computation resources and small size
of dataset, the model currently does not provide accurate translation. But the reader may feel free
to play with the model, suggest any improvements or train the model on a better training dataset