mikr/whisper-large2-hu-cv11

Whisper Large-v2 Hungarian CV11

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

• Loss: 0.3247
• Wer: 15.5944

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: 32
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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
0.0076	7.52	1000	0.2607	16.0332
0.0013	15.04	2000	0.2896	15.7842
0.0009	22.55	3000	0.3042	16.2378
0.0003	30.07	4000	0.3247	15.5944
0.0002	37.59	5000	0.3313	15.6004

Framework versions

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