Edit model card

Whisper Small gl

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9699
  • Wer: 15.4306

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: 64
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 5000

Training results

Training Loss Epoch Step Validation Loss Wer
0.1844 1.8182 1000 1.6681 13.8720
0.0708 3.6364 2000 1.7869 13.2062
0.0351 5.4545 3000 1.8885 14.2740
0.0196 7.2727 4000 1.9333 15.7785
0.0144 9.0909 5000 1.9699 15.4306

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
72
Safetensors
Model size
242M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for deepdml/whisper-small-gl-cv17-timestamps

Finetuned
(1835)
this model

Dataset used to train deepdml/whisper-small-gl-cv17-timestamps

Evaluation results