Whisper Small Ori vi

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: 1.2003
  • Wer: 31.8158

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 8
  • 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: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2733 2.2222 1000 1.0770 38.2958
0.081 4.4444 2000 1.2118 36.3836
0.0172 6.6667 3000 1.2445 34.6916
0.0023 8.8889 4000 1.2003 31.8158

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.4.0
  • Datasets 3.0.2
  • Tokenizers 0.20.0
Downloads last month
22
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 datdo2717/whisper-small-ori-vi2_1e4

Finetuned
(2103)
this model

Dataset used to train datdo2717/whisper-small-ori-vi2_1e4

Evaluation results