pho-whisper-tiny-finetune

This model is a fine-tuned version of vinai/PhoWhisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5816
• eval_wer: 0.2905
• eval_runtime: 1479.0121
• eval_samples_per_second: 3.931
• eval_steps_per_second: 0.328
• epoch: 0.4048
• step: 27000

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-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 6
• gradient_accumulation_steps: 4
• total_train_batch_size: 48
• total_eval_batch_size: 12
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• training_steps: 50000

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1