whisper-small-fr – AI Model by personalizedrefrigerator | AlphaNeural AI

You can deploy this model and start earning money today!

personalizedrefrigerator/
whisper-small-fr

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-small

endpoints_compatible

Views

No views yet

whisper-small-fr

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4643
Model Preparation Time: 0.008
Wer: 0.2201
Cer: 0.1131

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-07
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: linear
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Wer	Cer
0.3466	0.25	1000	0.5668	0.008	0.1995	0.1116
0.2898	0.5	2000	0.4981	0.008	0.1941	0.1062
0.3102	0.75	3000	0.5281	0.008	0.2053	0.1053
0.2918	1.0	4000	0.5244	0.008	0.2005	0.1061

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1