whisper-deep-deal

This model is a fine-tuned version of Masternlp/Whisper_model on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.9897
• eval_wer: 32.7686
• eval_runtime: 17584.7708
• eval_samples_per_second: 3.961
• eval_steps_per_second: 0.495
• epoch: 0.2553
• step: 8000

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: 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: 16000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.0a0+e000cf0ad9.nv24.10
• Datasets 3.2.0
• Tokenizers 0.21.0