small_en_dg_9_seg_40_atc

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

• eval_loss: 0.2305
• eval_wer: 8.0427
• eval_runtime: 910.4652
• eval_samples_per_second: 4.393
• eval_steps_per_second: 0.035
• epoch: 5.0
• step: 9230

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: 64
• eval_batch_size: 128
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.8
• num_epochs: 6

Framework versions

• Transformers 4.51.2
• Pytorch 2.2.1+cu121
• Datasets 3.6.0
• Tokenizers 0.21.4