openai/whisper-medium

This model is a fine-tuned version of openai/whisper-medium on the vumichien/preprocessed_jsut_jsss_css10_common_voice_11 dataset. It achieves the following results on the evaluation set:

Loss: 0.2836
Wer: 8.7213
Cer: 5.4698

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: 32
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 10000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.1106	1.1	1000	0.1827	10.3480	6.4784
0.0487	2.2	2000	0.1799	9.4764	5.9127
0.0243	3.29	3000	0.1950	9.2111	5.8069
0.0106	4.39	4000	0.2113	8.9713	5.5756
0.0054	5.49	5000	0.2325	8.6470	5.4041
0.0031	6.59	6000	0.2462	8.7078	5.4409
0.0014	7.68	7000	0.2608	8.7145	5.4849
0.0009	8.78	8000	0.2695	8.6301	5.3876
0.0004	9.88	9000	0.2794	8.6064	5.3528
0.0003	10.98	10000	0.2836	8.7213	5.4698

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0+cu117
Datasets 2.7.1.dev0
Tokenizers 0.13.2

Dataset used to train vumichien/whisper-medium-mix-ja

Evaluation results

Wer on mozilla-foundation/common_voice_11_0 ja
test set self-reported

8.721
Cer on mozilla-foundation/common_voice_11_0 ja
test set self-reported

5.470
WER on google/fleurs
test set self-reported

12.825
CER on google/fleurs
test set self-reported

7.797

View on Papers With Code

vumichien
/

whisper-medium-mix-ja

openai/whisper-medium

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for vumichien/whisper-medium-mix-ja

Dataset used to train vumichien/whisper-medium-mix-ja

Evaluation results