metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - PolyAI/minds14
metrics:
  - wer
model-index:
  - name: whisper-tiny-minds-v5-numproc1
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: PolyAI/minds14
          type: PolyAI/minds14
          config: en-US
          split: train[451:]
          args: en-US
        metrics:
          - name: Wer
            type: wer
            value: 0.37507453786523554

whisper-tiny-minds-v5-numproc1

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: 0.6530
Wer Ortho: 0.4102
Wer: 0.3751

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: linear
lr_scheduler_warmup_steps: 100
training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.4354	3.57	100	0.5542	0.4539	0.3870
0.066	7.14	200	0.5501	0.4059	0.3554
0.0086	10.71	300	0.6204	0.3953	0.3542
0.0028	14.29	400	0.6455	0.3990	0.3631
0.0022	17.86	500	0.6530	0.4102	0.3751

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3