matildecs/whisper-medium-sds200-w

whisper-medium-sds200

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

• Loss: 0.3825
• Wer: 23.8821

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: 6.25e-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4312	0.4327	1000	0.4365	26.9500
0.3347	0.8654	2000	0.4026	25.4442
0.2204	1.2981	3000	0.3905	24.7511
0.1884	1.7309	4000	0.3808	24.1108
0.1296	2.1636	5000	0.3825	23.8821

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1