This model is a fine-tuned version of openai/whisper-small on the aihub adult speed changed dataset. It achieves the following results on the evaluation set:

Loss: 0.2617
Cer: 6.5496

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use 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: 50
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.2443	0.1289	100	0.2948	7.8830
0.137	0.2579	200	0.2761	7.3719
0.1094	0.3868	300	0.2806	7.3719
0.1216	0.5158	400	0.2647	7.2192
0.0963	0.6447	500	0.2679	7.2310
0.0918	0.7737	600	0.2690	7.0312
0.0926	0.9026	700	0.2676	7.0371
0.0381	1.0316	800	0.2591	6.8139
0.0292	1.1605	900	0.2618	6.7552
0.0378	1.2895	1000	0.2625	6.6964
0.0327	1.4184	1100	0.2675	6.6671
0.0371	1.5474	1200	0.2620	6.6494
0.0317	1.6763	1300	0.2607	6.4967
0.0312	1.8053	1400	0.2599	6.4850
0.0321	1.9342	1500	0.2617	6.5496

Framework versions

Transformers 4.46.0.dev0
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0

Gummybear05/whisper-small-Ybaseline

whisper-small-Ypause

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Gummybear05/
whisper-small-Ybaseline