This model is a fine-tuned version of openai/whisper-small on the AshtonLKY/augmented_audio dataset.
It achieves the following results on the evaluation set:
eval_loss: 0.0084
eval_wer: 6.1320
eval_runtime: 3863.0969
eval_samples_per_second: 3.479
eval_steps_per_second: 0.217
epoch: 2.98
step: 10000
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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
