metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - lyhourt/clean_6
metrics:
  - wer
model-index:
  - name: whisper-small-clean_6-v5
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: lyhourt/clean_6
          type: lyhourt/clean_6
        metrics:
          - name: Wer
            type: wer
            value: 21.24038237351364

whisper-small-clean_6-v5

This model is a fine-tuned version of openai/whisper-small on the lyhourt/clean_6 dataset. It achieves the following results on the evaluation set:

Loss: 0.2706
Wer: 21.2404

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: 64
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
training_steps: 1500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1461	0.9452	500	0.2746	23.0473
0.0631	1.8904	1000	0.2693	21.5318
0.0334	2.8355	1500	0.2706	21.2404

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1