Whisper Turbo Five 5K - Chee Li

This model is a fine-tuned version of openai/whisper-base on the Google Fleurs dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1982
  • Wer: 8.3488

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: 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: 600
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0903 1.0560 1000 0.1948 9.9042
0.0389 2.1119 2000 0.1943 9.3442
0.0212 3.1679 3000 0.1958 9.0828
0.0075 4.2239 4000 0.1961 8.4626
0.0018 5.2798 5000 0.1982 8.3488

Framework versions

  • Transformers 4.43.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
9
Safetensors
Model size
809M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for CheeLi03/whisper-tb-5k

Finetuned
(366)
this model