whisper-small-reverse-ml-mft-1-exp

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

• Loss: 0.0788
• Wer: 43.8497
• Cer: 14.0938

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: 0.0002
• train_batch_size: 64
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: warmup_stable_decay
• lr_scheduler_warmup_steps: 593
• training_steps: 5928

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.0698	1.0	1482	0.0952	50.9644	17.3791
0.058	2.0	2964	0.0822	47.1310	15.6959
0.0501	3.0	4446	0.0812	45.5018	15.0481
0.0366	4.0	5928	0.0788	43.8497	14.0938

Framework versions

• Transformers 4.51.1
• Pytorch 2.8.0+cu128
• Datasets 4.4.1
• Tokenizers 0.21.4