trocr-finetuned

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

eval_loss: 0.7032
eval_cer: 0.1351
eval_wer: 0.4206
eval_cer_case_insensitive: 0.1140
eval_wer_case_insensitive: 0.3465
eval_runtime: 327.1438
eval_samples_per_second: 2.559
eval_steps_per_second: 0.642
epoch: 1.5707
step: 2100

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: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 75
num_epochs: 12

Framework versions

Transformers 4.49.0
Pytorch 2.8.0+cu126
Datasets 4.4.2
Tokenizers 0.21.4

Downloads last month: 3

Safetensors

Model size

0.6B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for alterf/trocr-finetuned

Base model

microsoft/trocr-large-handwritten

Finetuned

(15)

this model