You can deploy this model and start earning money today!

Rziane/
whisper-large-v3-turbo-CAENNAIS_GBv2

Name: whisper-large-v3-turbo-CAENNAIS_GBv2
Availability: InStock

Views

No views yet

whisper-large-v3-turbo-CAENNAIS_GBv2

This model is a fine-tuned version of Rziane/whisper-large-v3-turbo-CAENNAIS_GB on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 32
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
lr_scheduler_warmup_steps: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	94	0.5230	18.2036
No log	2.0	188	0.5634	19.1121
No log	3.0	282	0.5417	19.5749
No log	4.0	376	0.5800	20.6376
No log	5.0	470	0.5756	21.9232
0.0196	6.0	564	0.5970	21.5118
0.0196	7.0	658	0.5947	20.1748
0.0196	8.0	752	0.5755	20.7405
0.0196	9.0	846	0.5800	18.6836
0.0196	10.0	940	0.5832	19.1121