stammer-small

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: 0.4497
  • Wer: 35.7430

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: 10
  • training_steps: 100
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.9039 0.3968 25 0.7568 42.1687
0.4742 0.7937 50 0.4766 35.9438
0.3073 1.1905 75 0.4589 35.1406
0.3061 1.5873 100 0.4497 35.7430

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.1.0+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
24
Safetensors
Model size
242M 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 stillerman/stammer-small

Finetuned
(2105)
this model