Whisper Small en - pbl4

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:

  • eval_loss: 0.3805
  • eval_wer: 10.6595
  • eval_runtime: 58.6535
  • eval_samples_per_second: 2.557
  • eval_steps_per_second: 0.324
  • epoch: 227.2727
  • step: 5000

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

image/png

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • 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: 6000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.4.0
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
92
Safetensors
Model size
242M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for cang1602004/whisper-small-en

Finetuned
(2311)
this model

Dataset used to train cang1602004/whisper-small-en