san2003m/whisper-small-hi

Whisper Small ATC - ATCText

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

• eval_loss: 1.9991
• eval_wer: 76.1224
• eval_runtime: 2033.5597
• eval_samples_per_second: 2.323
• eval_steps_per_second: 0.066
• epoch: 0.0
• step: 1

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: 0.1
• train_batch_size: 32
• eval_batch_size: 35
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 2
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2