Translation
Keras
Khmer
bigru-additive-attention-seq2seq
transliteration
khmer
romanization
seq2seq
gru
attention
Eval Results (legacy)
Instructions to use Netra-Lab/AkaraAlpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use Netra-Lab/AkaraAlpha with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://Netra-Lab/AkaraAlpha") - Notebooks
- Google Colab
- Kaggle
Download config.json from Netra-Lab/AkaraAlpha: direct link, hf CLI and curl.
- Browser
- Download file 676 Bytes
-
https://huggingface.co/Netra-Lab/AkaraAlpha/resolve/main/config.json
- Command line
-
hf download hf://Netra-Lab/AkaraAlpha/config.json
-
curl -L -o config.json https://huggingface.co/Netra-Lab/AkaraAlpha/resolve/main/config.json
676 Bytes
| { | |
| "model_type": "bigru-additive-attention-seq2seq", | |
| "framework": "keras", | |
| "keras_file": "bi_gru_attention_khmer_transliterator.keras", | |
| "embedding_dim": 32, | |
| "encoder": { | |
| "type": "bidirectional_gru", | |
| "units_per_direction": 64 | |
| }, | |
| "encoder_projection": 64, | |
| "decoder": { | |
| "type": "gru", | |
| "units": 64, | |
| "initial_state": "zeros" | |
| }, | |
| "attention": { | |
| "type": "additive", | |
| "use_scale": true | |
| }, | |
| "latin_vocab_size": 28, | |
| "khmer_vocab_size": 81, | |
| "max_latin_len": 25, | |
| "max_khmer_len": 24, | |
| "parameters": 78705, | |
| "dictionary_file": "khmer_dictionary.txt", | |
| "dictionary_words": 38743, | |
| "recommended_beam_width": 5, | |
| "max_edit_distance": 2 | |
| } | |