whisper_large_v3_fixed_timestamps

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: 0.7134
• Cer: 18.1073
• Wer: 28.9480

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: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
1.2369	1.0	6265	0.7964	28.2902	43.3188
0.7051	2.0	12530	0.7422	25.7611	39.1987
0.5951	3.0	18795	0.7247	21.2559	33.7121
0.521	4.0	25060	0.7196	19.0071	30.5013
0.471	5.0	31325	0.7134	18.1073	28.9480

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1