sgangireddy/whisper-small-en-sandi

openai/whisper-small.en

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

• Loss: 1.3087
• Wer: 25.5445

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0021	10.0033	1000	1.1983	25.8346
0.0005	20.0067	2000	1.2810	25.4955
0.0002	30.01	3000	1.3087	25.5445

Framework versions

• Transformers 4.49.0
• Pytorch 2.4.0+cu121
• Datasets 3.3.2
• Tokenizers 0.21.0