Whisper Small nl

This model is a fine-tuned version of openai/whisper-small on the procit009/nl_stt dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2637
  • Wer: 14.1492

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: 16
  • eval_batch_size: 5
  • seed: 42
  • optimizer: Use 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: 200
  • num_epochs: 6
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2302 1.0 125 0.2444 14.2023
0.1247 2.0 250 0.2396 14.4464
0.036 3.0 375 0.2448 13.9582
0.0117 4.0 500 0.2549 14.0113
0.0049 5.0 625 0.2604 15.5928
0.0031 6.0 750 0.2637 14.1492

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
32
Safetensors
Model size
242M 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 procit009/whisper_finetune

Finetuned
(2144)
this model

Dataset used to train procit009/whisper_finetune