Whisper Small Hi - NoumidaA_2

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2872
  • Wer: 34.6694

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • 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: 10
  • training_steps: 2500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.219 0.6116 500 0.3216 41.6871
0.1 1.2226 1000 0.2960 38.3941
0.1034 1.8343 1500 0.2831 37.2090
0.043 2.4453 2000 0.2893 35.1393
0.0164 3.0563 2500 0.2872 34.6694

Framework versions

  • Transformers 4.53.0
  • Pytorch 2.6.0+cu124
  • Datasets 3.6.0
  • Tokenizers 0.21.2
Downloads last month
35
Safetensors
Model size
242M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Noumida/whisper-small-hi

Finetuned
(2793)
this model

Dataset used to train Noumida/whisper-small-hi

Spaces using Noumida/whisper-small-hi 2

Evaluation results