This model is a fine-tuned version of emilios/whisper-medium-el-n2 on the mozilla-foundation/common_voice_11_0 el dataset. It achieves the following results on the evaluation set:

Loss: 0.5669
Wer: 9.8997

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: 3e-06
train_batch_size: 32
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 11000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0014	58.82	1000	0.4951	10.3640
0.0006	117.65	2000	0.5181	10.2805
0.0007	175.82	3000	0.5317	10.1133
0.0004	234.65	4000	0.5396	10.1226
0.0004	293.47	5000	0.5532	10.1040
0.0013	352.29	6000	0.5645	10.0854
0.0002	411.12	7000	0.5669	10.1133
0.0001	469.94	8000	0.5669	9.8997
0.0001	528.76	9000	0.5645	9.9276
0.0001	587.82	10000	0.5674	9.9647
0.0003	646.82	11000	0.5669	9.9461

Framework versions

Transformers 4.26.0.dev0
Pytorch 2.0.0.dev20221216+cu116
Datasets 2.7.1.dev0
Tokenizers 0.13.2

emilios/whisper-medium-el-n3

Whisper medium Greek El Greco

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

emilios/
whisper-medium-el-n3