whisper-tiny_to_japanese_accent_finetune – AI Model by Clo123 | AlphaNeural AI

You can deploy this model and start earning money today!

Clo123/
whisper-tiny_to_japanese_accent_finetune

like

0

automatic-speech-recognition

hf-asr-leaderboard

generated_from_trainer

Japanese_english

openai/whisper-tiny

endpoints_compatible

Views

No views yet

Whisper tiny Japanese fine tuned 2

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

Loss: 0.4629
Wer: 21.5382

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
0.4175	0.3109	250	0.6061	32.1115
0.336	0.6219	500	0.5250	28.2268
0.3891	0.9328	750	0.4928	23.0576
0.1376	1.2438	1000	0.4816	22.1805
0.1428	1.5547	1250	0.4762	23.1203
0.1484	1.8657	1500	0.4621	21.4756
0.0393	2.1766	1750	0.4598	21.5069
0.0903	2.4876	2000	0.4629	21.5382

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1