whisper-large-v3-ft-btb-cy

This model is a fine-tuned version of openai/whisper-large-v3 on the DewiBrynJones/banc-trawsgrifiadau-bangor-clean train 2410 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4687
• Wer: 0.2887

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
0.4429	0.8580	1000	0.4673	0.3495
0.3192	1.7160	2000	0.4116	0.2986
0.1917	2.5740	3000	0.4086	0.2937
0.1113	3.4320	4000	0.4341	0.2852
0.0665	4.2900	5000	0.4687	0.2887

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1