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 default dataset. It achieves the following results on the evaluation set:

• Loss: 0.5776
• Wer: 0.3064

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
0.3674	1.1390	1000	0.4709	0.3416
0.2228	2.2779	2000	0.4358	0.3117
0.1266	3.4169	3000	0.4588	0.3070
0.0611	4.5558	4000	0.5140	0.3039
0.0245	5.6948	5000	0.5776	0.3064

Framework versions

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