whisper-large-v3-natbed-native-model

This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8157
• Wer: 53.5669

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: 1.75e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 30000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.4403	0.7013	250	0.8207	61.9634
0.7263	1.4025	500	0.7642	56.5183
0.6316	2.1038	750	0.7486	54.5928
0.4615	2.8050	1000	0.7218	51.1206
0.3381	3.5063	1250	0.7561	52.2569
0.2662	4.2076	1500	0.8242	52.5095
0.1788	4.9088	1750	0.8157	53.5669

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1