whisper-tiny-sna-candace

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: 0.5942
• Wer: 0.3448
• Cer: 0.1006

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• 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
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.3383	2.3364	500	0.4698	0.3734	0.1221
0.2076	4.6729	1000	0.4397	0.3577	0.1154
0.1097	7.0093	1500	0.4844	0.3578	0.1072
0.0328	9.3458	2000	0.5545	0.3479	0.1018
0.0185	11.6822	2500	0.5942	0.3448	0.1006

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2