kushpatel49/whisper-base-hii

Whisper Base Hi - Fleurs

This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7908
• Wer: 41.0289

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: 64
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0038	52.6486	1000	0.5998	40.2382
0.0004	105.2703	2000	0.7257	40.9313
0.0002	157.9189	3000	0.7754	40.6384
0.0002	210.5405	4000	0.7908	41.0289

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.1