rangsitra-whisper-sm-append-0.1 – AI Model by SmartWhatt | AlphaNeural AI

You can deploy this model and start earning money today!

SmartWhatt/
rangsitra-whisper-sm-append-0.1

like

0

automatic-speech-recognition

generated_from_trainer

mozilla-foundation/common_voice_17_0

openai/whisper-small

endpoints_compatible

Views

No views yet

Rangsitra Whisper

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:

Cer: 6.1968
Wer: 20.8539
Loss: 0.1819

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: 16
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: warmup_stable_decay
lr_scheduler_warmup_steps: 1220
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Cer	Wer	Validation Loss
0.2015	1.0	2441	9.4469	31.3201	0.2031
0.1232	2.0	4882	7.3926	25.0740	0.1723
0.0719	3.0	7323	7.1415	23.8172	0.1772
0.0222	4.0	9764	6.3715	21.5247	0.1764
0.0086	5.0	12205	6.1968	20.8539	0.1819

Framework versions

Transformers 4.52.4
Pytorch 2.9.1+cu128
Datasets 3.6.0
Tokenizers 0.21.4