Downloads · 30 days
3
1% of all-time downloads
char-lstm-seq2seq
keras-io/char-lstm-seq2seq
char-lstm-seq2seq is a translation model from keras-io. Use it when you need text moved from one language to another. It is set up for tf-keras. The card lists the license as cc0-1.0.
This repo contains the model and the notebook to this Keras example on Character-level recurrent sequence-to-sequence model.
All-time downloads
527
Public
Repo size
1.5 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.data-00000-of-000012.9 MB · 65%
At a glance
- Task
- Translation
- Library
- tf-keras
- License
- cc0-1.0
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Feb 6, 2022
- SHA
- 08aadb65
Try a prompt
Model card
From the Hugging Face model README
Keras Implementation of Character-level recurrent sequence-to-sequence model
This repo contains the model and the notebook to this Keras example on Character-level recurrent sequence-to-sequence model.
Full credits to: fchollet
Background Information
This example demonstrates how to implement a basic character-level recurrent sequence-to-sequence model. We apply it to translating short English sentences into short French sentences, character-by-character. Note that it is fairly unusual to do character-level machine translation, as word-level models are more common in this domain.
Limitations
It works on text of length <= 15 characters
Parameters needed for using the model
latent_dim = 256
num_encoder_tokens = 71
max_encoder_seq_length = 15
num_decoder_tokens = 92
max_decoder_seq_length = 59
- Task
- Translation
- Library
- tf-keras
- License
- cc0-1.0
- Languages
- en, fr
- Created
- Mar 2, 2022
- Updated
- Feb 6, 2022