maag/whisper_tiny_cs

Whisper tiny Czech CV13 v1

This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_13_0 cs dataset. It achieves the following results on the evaluation set:

• Loss: 0.5430
• Wer: 44.0802

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
• distributed_type: multi-GPU
• num_devices: 3
• gradient_accumulation_steps: 4
• total_train_batch_size: 384
• total_eval_batch_size: 48
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1007	21.86	1000	0.5430	44.0802
0.013	43.72	2000	0.6489	44.9182
0.0079	65.57	3000	0.6782	45.5169

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3