Edit model card

whisper-small-300v2

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

  • Loss: 0.9642
  • Wer Ortho: 67.5676
  • Wer: 67.5676

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 30
  • training_steps: 300

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.8789 20.0 60 1.2473 70.2703 70.2703
0.0015 40.0 120 0.9230 72.9730 72.9730
0.0 60.0 180 0.9398 67.5676 67.5676
0.0 80.0 240 0.9529 67.5676 67.5676
0.0 100.0 300 0.9642 67.5676 67.5676

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
242M params
Tensor type
F32
·
Inference API
or
This model can be loaded on Inference API (serverless).

Finetuned from

Evaluation results