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
Label the spec table columns
Browse filesThe empty header row rendered as a blank strip.
README.md
CHANGED
|
@@ -49,7 +49,7 @@ The code is on [GitHub](https://github.com/netra-ai-lab/Romanized-Khmer-to-Khmer
|
|
| 49 |
|
| 50 |
*AkaraAlpha turning `brodae` into ααααα.* The encoder reads upwards: each letter becomes a 32-dimensional embedding, a bidirectional GRU reads the letters in both directions, and a projection brings each state to 64 dimensions, the keys and values for attention. The decoder reads downwards. At step 4, with α α α written, its GRU output is the query for additive attention, and a softmax layer over 81 ids gives α with probability 0.997. The chosen character joins the input and the loop repeats until the end marker.
|
| 51 |
|
| 52 |
-
| | |
|
| 53 |
| --- | --- |
|
| 54 |
| Input | Romanized word, up to 25 characters: 26 Latin letters |
|
| 55 |
| Output | Khmer word, up to 24 characters: 77 Khmer characters |
|
|
|
|
| 49 |
|
| 50 |
*AkaraAlpha turning `brodae` into ααααα.* The encoder reads upwards: each letter becomes a 32-dimensional embedding, a bidirectional GRU reads the letters in both directions, and a projection brings each state to 64 dimensions, the keys and values for attention. The decoder reads downwards. At step 4, with α α α written, its GRU output is the query for additive attention, and a softmax layer over 81 ids gives α with probability 0.997. The chosen character joins the input and the loop repeats until the end marker.
|
| 51 |
|
| 52 |
+
| Part | Setting |
|
| 53 |
| --- | --- |
|
| 54 |
| Input | Romanized word, up to 25 characters: 26 Latin letters |
|
| 55 |
| Output | Khmer word, up to 24 characters: 77 Khmer characters |
|