impaired-v3-independent-all-hc-train

This model is a fine-tuned version of honzapucalek/hc-czech-large-v3-v2-independent on the honzapucalek/impaired_v3_independent_all cs dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4176
  • Wer: 0.4059

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.006 13.99 1000 1.1860 0.4332
0.0022 27.97 2000 1.1733 0.4211
0.0001 41.96 3000 1.3533 0.4109
0.0 55.94 4000 1.4029 0.4099
0.0 69.93 5000 1.4176 0.4059

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
Downloads last month
17
Safetensors
Model size
1.54B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for honzapucalek/impaired-v3-independent-all-hc-train

Finetuned
(1)
this model

Evaluation results