whisper-large-v3-czech-cv13/README.md

license, base_model, tags, metrics, model-index

license	base_model	tags	metrics	model-index
apache-2.0	openai/whisper-large-v3	generated_from_trainer	wer	name results openai/whisper-large-v3

openai/whisper-large-v3

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1283
• Wer: 0.0789

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: 62
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• 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
0.0138	2.24	1000	0.0962	0.0863
0.004	4.48	2000	0.1117	0.0844
0.0015	6.73	3000	0.1178	0.0807
0.0004	8.97	4000	0.1219	0.0792
0.0002	11.21	5000	0.1283	0.0789

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.0.0+cu117
• Datasets 2.14.6
• Tokenizers 0.14.1