Instructions to use RinKana/eng-jpn-transformer-nmt-efficient with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use RinKana/eng-jpn-transformer-nmt-efficient with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://RinKana/eng-jpn-transformer-nmt-efficient") - Notebooks
- Google Colab
- Kaggle
English-Japanese Transformer
Model Transformer untuk terjemahan English → Japanese, dilatih dengan Keras 3.
Performance
- Validation Accuracy: 0.9129
- Average Character BLEU Score: 0.2440
Usage
Model ini dapat dimuat dan digunakan dengan tokenizers yang disediakan.
import keras
# Memuat model penuh
model = keras.models.load_model("model_upload/transformer_model.keras")
# Lanjutkan dengan proses decode_sequence yang sudah Anda sempurnakan
- Downloads last month
- 5