mikr/whisper-medium-czech-cv11

Whisper Medium Czech 2 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: 0.2417
• Wer: 11.4086

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: 32
• seed: 42
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0105	4.24	1000	0.1973	12.6130
0.0016	8.47	2000	0.2198	11.8985
0.0004	12.71	3000	0.2310	11.4547
0.0003	16.95	4000	0.2380	11.4270
0.0002	21.19	5000	0.2417	11.4086

Framework versions

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