whisper-lg-el-intlv-xs

This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0,google/fleurs el,el_gr dataset. It achieves the following results on the evaluation set:

• Loss: 0.2913
• 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: 3.5e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0311	2.49	1000	0.1809	10.5498
0.0074	4.98	2000	0.2470	10.2805
0.0019	7.46	3000	0.3008	10.0297
0.0011	9.95	4000	0.2913	9.8997
0.0009	12.44	5000	0.3092	10.1876
0.0005	14.93	6000	0.3495	10.1969
0.0002	17.41	7000	0.3659	10.2526
0.0001	19.9	8000	0.3846	10.2619
0.0001	22.39	9000	0.3941	10.2897
0.0001	24.88	10000	0.3990	10.3269

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2