This model is a fine-tuned version of openai/whisper-small on the Homophones in Common Voice 15.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.2203
Wer: 15.6119

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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
0.1884	0.25	1000	0.2626	17.6905
0.1992	0.5	2000	0.2414	14.0762
0.1937	0.75	3000	0.2298	15.1048
0.1672	1.0	4000	0.2203	15.6119

Framework versions

Transformers 4.36.0.dev0
Pytorch 1.12.1+cu113
Datasets 2.15.0
Tokenizers 0.15.0

kiriku/whisper-large-en-homophone

Homophones_filted_dataset Whisper large en

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

kiriku/
whisper-large-en-homophone