re-skill/whisper-large-v3-turbo-tj

whisper-tajik-moar-low-lr

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

• Loss: 0.2667
• Wer: 16.4316

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: 5e-05
• train_batch_size: 128
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.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
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1505	1.0	704	0.3244	23.0135
0.1011	2.0	1408	0.2744	18.8362
0.0635	3.0	2112	0.2646	17.0636
0.0328	4.0	2816	0.2667	16.4316

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.4