whisper-cv-cy-train-all-plus-other-with-excluded-ft-cv-tts

This model is a fine-tuned version of DewiBrynJones/whisper-large-v3-ft-cv-cy-train-all-plus-other-with-excluded on the DewiBrynJones/commonvoice_cy_tts train main dataset. It achieves the following results on the evaluation set:

• Loss: 0.2556
• Wer: 0.1934

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.23	0.4583	1000	0.2574	0.1992
0.1775	0.9166	2000	0.2527	0.2015
0.0978	1.3749	3000	0.2559	0.1951
0.0902	1.8332	4000	0.2556	0.1934

Framework versions

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