whisper-small-ru-v14tsb

This model is a fine-tuned version of constantinedivis/whisper-small-ru-v14tsb on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1003
• Wer: 8.8926

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: 32
• eval_batch_size: 32
• 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: 400
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0538	0.1916	200	0.1289	11.2867
0.0401	0.3831	400	0.1276	10.6498
0.0729	0.5747	600	0.1237	10.6616
0.1103	0.7663	800	0.1056	9.4587
0.1032	0.9579	1000	0.1003	8.8926

Framework versions

• Transformers 4.49.0
• Pytorch 2.1.0+cu118
• Datasets 3.3.2
• Tokenizers 0.21.0