rogramss/whisper-tiny_to_british_accent_further_analysis_th

Whisper tiny Chinese

This model is a fine-tuned version of openai/whisper-tiny on the British English 'TH' Phonemes dataset. It achieves the following results on the evaluation set:

• Loss: 0.3769
• Wer: 13.7767

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: 1
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0564	3.5714	500	0.3415	14.0934
0.0009	7.1429	1000	0.3557	14.1726
0.0004	10.7143	1500	0.3715	13.8559
0.0003	14.2857	2000	0.3769	13.7767

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1