README.md

metadata

library_name: transformers
tags:
  - generated_from_trainer
metrics:
  - wer
  - bleu
model-index:
  - name: ethiopic-sec2sec-supervised
    results: []

ethiopic-sec2sec-supervised

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1136
• Wer: 0.0503
• Cer: 0.0127
• Bleu: 90.3096

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 64
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer	Bleu
0.1032	1.0	40338	0.1136	0.0503	0.0127	90.3096

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1