whisper-tiny-high-mixed-pt

This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 256
eval_batch_size: 8
seed: 42
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_ratio: 0.1
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
0.7518	0.4348	50	0.5783
0.5948	0.8696	100	0.5103
0.4252	1.3043	150	0.4845
0.416	1.7391	200	0.4667
0.2896	2.1739	250	0.4568
0.2679	2.6087	300	0.4542
0.2632	3.0435	350	0.4488
0.1817	3.4783	400	0.4614
0.1874	3.9130	450	0.4531
0.13	4.3478	500	0.4695
0.1328	4.7826	550	0.4690
0.0891	5.2174	600	0.4786
0.0943	5.6522	650	0.4871
0.0814	6.0870	700	0.4954
0.0685	6.5217	750	0.4940
0.0676	6.9565	800	0.5017
0.0502	7.3913	850	0.5080
0.0505	7.8261	900	0.5109
0.0408	8.2609	950	0.5170
0.039	8.6957	1000	0.5190
0.036	9.1304	1050	0.5204
0.0316	9.5652	1100	0.5239
0.0335	10.0	1150	0.5240