metadata

language:
  - en-us
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - PolyAI/minds14
metrics:
  - wer
model-index:
  - name: whisper tiny en-US - J3
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: PolyAI/minds14-en-US
          type: PolyAI/minds14
          config: en-US
          split: train[450:]
          args: en-US
        metrics:
          - name: Wer
            type: wer
            value: 0.3654073199527745

whisper tiny en-US - J3

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14-en-US dataset. It achieves the following results on the evaluation set:

Loss: 1.0413
Wer Ortho: 0.3603
Wer: 0.3654

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: reduce_lr_on_plateau
lr_scheduler_warmup_steps: 100
training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0001	35.71	500	0.8505	0.3430	0.3459
0.0	71.43	1000	0.9093	0.3455	0.3501
0.0	107.14	1500	0.9707	0.3553	0.3589
0.0	142.86	2000	1.0413	0.3603	0.3654

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3