Edit model card

Whisper Large V2

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4546
  • Wer: 13.7562

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: 3e-05
  • train_batch_size: 16
  • 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: 20
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Wer
0.7616 0.55 30 0.4375 24.4768
0.3849 1.09 60 0.4161 15.6734
0.2127 1.64 90 0.3971 16.5841
0.1689 2.18 120 0.4066 15.6415
0.0923 2.73 150 0.4113 14.6509
0.0685 3.27 180 0.4229 13.4367
0.0415 3.82 210 0.4213 14.2355
0.0224 4.36 240 0.4511 13.6923
0.0155 4.91 270 0.4546 13.7562

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.0
Downloads last month
3
Safetensors
Model size
1.54B params
Tensor type
F32
·

Finetuned from