mikr/whisper-medium-cs-cv11

Whisper Medium Czech CV11

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

• Loss: 0.2537
• Wer: 11.6893

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0384	2.02	1000	0.2167	13.5467
0.0061	4.03	2000	0.2373	12.9172
0.0018	6.05	3000	0.2407	12.0409
0.0007	8.07	4000	0.2463	11.7685
0.0003	10.09	5000	0.2537	11.6893

Framework versions

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