whisper-small-en-cv-1.1 – AI Model by xbilek25 | AlphaNeural AI

You can deploy this model and start earning money today!

xbilek25/
whisper-small-en-cv-1.1

like

0

automatic-speech-recognition

generated_from_trainer

mozilla-foundation/common_voice_17_0

openai/whisper-small

endpoints_compatible

Views

No views yet

Whisper small v1.1

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.4405
Wer: 17.2902

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-06
train_batch_size: 32
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: 400
training_steps: 3600
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2216	5.0097	600	0.3246	14.2857
0.1061	10.0194	1200	0.3383	15.3628
0.0556	15.0292	1800	0.3790	16.3265
0.0228	21.0075	2400	0.4160	16.4966
0.0186	26.0172	3000	0.4344	16.8934
0.018	31.0269	3600	0.4405	17.2902

Framework versions

Transformers 4.51.1
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1