You can deploy this model and start earning money today!

thunderboltc/
whisper-small-santali-sanlish-1207

Name: whisper-small-santali-sanlish-1207
Availability: InStock

Views

No views yet

whisper-small-santali-sanlish-1207

This model is a fine-tuned version of thunderboltc/whisper-small-santali-sanlish-1207 on the None 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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 153
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.0008	1.0	62	1.0570	45.5631	9.9226
0.0233	2.0	124	1.1563	49.1468	10.8071
0.0522	3.0	186	1.0669	50.0	11.4151
0.0623	4.0	248	1.0732	47.7816	10.3925
0.0270	5.0	310	1.0903	47.7816	10.3648
0.0162	6.0	372	1.1659	47.2696	10.2266