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: 0.5452
• Wer: 84.0883

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0869	6.25	200	0.3877	89.5470
0.0138	12.5	400	0.4962	87.4564
0.0088	18.75	600	0.5118	100.3484
0.0058	25.0	800	0.5452	84.0883

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.14.0