Noumida/whisper-small-ml2

Whisper Small Ml - NoumidaA_2

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

• Loss: 0.5718
• Wer: 82.5287

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: 10
• training_steps: 2500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0184	9.2593	500	0.4492	83.9080
0.0021	18.5185	1000	0.5179	83.2184
0.0001	27.7778	1500	0.5468	83.4483
0.0	37.0370	2000	0.5664	82.5287
0.0	46.2963	2500	0.5718	82.5287

Framework versions

• Transformers 4.53.0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2