You can deploy this model and start earning money today!

tuan8p/
whisper-small-vi

Name: whisper-small-vi
Availability: InStock

automatic-speech-recognition

generated_from_trainer

Views

No views yet

Whisper Small Vi - tuan8p

This model is a fine-tuned version of openai/whisper-small on the Custom dataset for ASR dataset. It achieves the following results on the evaluation set:

Loss: 0.0494
Wer: 0.0332

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: 8
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
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.5174	1.0	22	1.5900	0.6739
1.2002	2.0	44	0.9756	0.4358
0.5622	3.0	66	0.3502	0.2107
0.1565	4.0	88	0.1417	0.0779
0.0626	5.0	110	0.0765	0.0418
0.035	6.0	132	0.0626	0.0418
0.0209	7.0	154	0.0551	0.0332
0.0124	8.0	176	0.0505	0.0289
0.0067	9.0	198	0.0572	0.0433
0.0076	10.0	220	0.0494	0.0332

Framework versions

Transformers 4.52.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

tuan8p/whisper-small-vi

Whisper Small Vi - tuan8p

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tuan8p/
whisper-small-vi