metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - PolyAI/minds14
metrics:
  - wer
model-index:
  - name: whisper-tiny
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: PolyAI/minds14
          type: PolyAI/minds14
          config: en-US
          split: train
          args: en-US
        metrics:
          - name: Wer
            type: wer
            value: 0.4167650531286895

whisper-tiny

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

Loss: 0.6416
Wer Ortho: 0.4448
Wer: 0.4168

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: 3e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 125
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0592	0.89	25	0.6009	0.4226	0.3808
0.0508	1.79	50	0.6093	0.4485	0.4103
0.0483	2.68	75	0.6205	0.4442	0.4126
0.0315	3.57	100	0.6268	0.4392	0.4120
0.0304	4.46	125	0.6416	0.4448	0.4168

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.2
Datasets 2.16.1
Tokenizers 0.15.0