xbilek25/whisper-small-train-csen-p5concat

Whisper small + 2000 csen p5 concacat

This model is a fine-tuned version of openai/whisper-small on the Prvni fine tuning spolecnych speakeru dataset. It achieves the following results on the evaluation set:

• Loss: 0.5955
• Wer: 32.2286

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 800
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2369	1.09	200	0.5234	35.9820
0.0817	3.03	400	0.5461	35.6588
0.0192	4.12	600	0.5798	32.1176
0.011	6.06	800	0.5955	32.2286

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2