mikr/whisper-large-czech-cv11

Whisper Large Czech CV11

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

• Loss: 0.2528
• Wer: 10.8278

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: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0058	4.02	1000	0.2097	11.9563
0.0012	8.04	2000	0.2210	10.9751
0.001	13.01	3000	0.2405	11.3488
0.0002	17.02	4000	0.2467	10.8794
0.0001	21.04	5000	0.2528	10.8278

Framework versions

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