whisper-tiny-CAENNAIS_GB_all

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

• Loss: 0.7755
• Wer: 38.9784

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: 16
• 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	94	1.8320	90.7782
No log	2.0	188	1.0804	49.2801
No log	3.0	282	0.8987	45.9719
No log	4.0	376	0.8173	47.2746
No log	5.0	470	0.7714	48.9544
1.1017	6.0	564	0.7526	45.6119
1.1017	7.0	658	0.7535	38.4985
1.1017	8.0	752	0.7628	38.9613
1.1017	9.0	846	0.7714	38.7041
1.1017	10.0	940	0.7755	38.9784

Framework versions

• Transformers 4.46.2
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.0