whisper_large_v3_turbo_annota_2

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the whisper_large_v3_turbo_annota_2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3910
• Wer: 21.8867

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: 6000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4409	0.3333	2000	0.4489	23.5761
0.4317	0.6667	4000	0.4141	22.9669
0.3881	1.0	6000	0.3910	21.8867

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3