Whisper pfe - bika5

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

  • Loss: 3.6101
  • Model Preparation Time: 0.006
  • Wer: 92.9204

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: 500
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Model Preparation Time Wer
0.0001 83.3333 1000 3.5216 0.006 92.9204
0.0 166.6667 2000 3.6101 0.006 92.9204

Framework versions

  • Transformers 4.43.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
2
Safetensors
Model size
242M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for bika5/whisper_pfe

Finetuned
(44)
this model

Dataset used to train bika5/whisper_pfe

Evaluation results