whisper-small-ml

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5825
• Wer: 86.7596

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
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 800

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0871	6.25	200	0.3892	91.2892
0.0159	12.5	400	0.4824	87.3403
0.0087	18.75	600	0.5296	85.2497
0.0063	25.0	800	0.5825	86.7596

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1