Modelpublic

kinlas/Kumamoto-to-hyojun-converter

sourceHugging Faceupdated 10mo agoView on Hugging Face

0likes7downloads

Model Card

checkpoint = "google/mt5-small" tokenizer = MT5Tokenizer.frompretrained(checkpoint, legacy=False) model = MT5ForConditionalGeneration.frompretarined(checkpoint)

—This model is katakana-oriented.
—CharacTER score = 0.3443

Training

—Trainer: Seq2seqTrainer
—Epochs: 200
—Optimizer: AdamW
—Learning Rate: 2e-5
—Weight decay: 0.01
—Warm-ups: 0.05*total_steps
—Scheduler: cosine