emilios/whisper-medium-el-n2

Whisper medium Greek El Greco

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

• Loss: 0.4656
• Wer: 10.6426

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: 4e-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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0066	111.11	1000	0.2357	23.0441
0.0024	222.22	2000	0.2607	19.6657
0.0011	333.33	3000	0.2771	20.8748
0.0043	234.82	4000	0.4536	10.7077
0.0024	293.65	5000	0.4656	10.6426

Framework versions

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