Edit model card

whisper-small-akan

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

  • Loss: 1.1860
  • Wer: 48.9551

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: 0.0001
  • train_batch_size: 32
  • 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 Wer
0.1893 10.0 250 0.8613 62.1906
0.0452 20.0 500 0.9964 55.3579
0.0211 30.0 750 1.0689 52.0824
0.0069 40.0 1000 1.1229 52.2306
0.0008 50.0 1250 1.1646 49.0885
0.0002 60.0 1500 1.1773 49.2663
0.0002 70.0 1750 1.1838 49.0885
0.0002 80.0 2000 1.1860 48.9551

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
37.8M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for devkyle/whisper-small-dp-v4

Finetuned
(1884)
this model