whisper-small-ru-v9lb

This model is a fine-tuned version of constantinedivis/whisper-small-ru-v8lb on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1069
• Wer: 9.5530

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
0.0973	0.1934	200	0.1316	10.7678
0.0813	0.3868	400	0.1326	10.7088
0.0967	0.5803	600	0.1204	10.5791
0.0787	0.7737	800	0.1124	10.0719
0.071	0.9671	1000	0.1069	9.5530

Framework versions

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