whisper-large-v2-2swissdatasets

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2491
• Wer: 16.5053

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: 5e-06
• 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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2827	0.0780	1000	0.3166	20.3350
0.2452	0.1560	2000	0.2901	18.7233
0.2336	0.2340	3000	0.2697	17.6650
0.2519	0.3120	4000	0.2563	16.8885
0.2295	0.3900	5000	0.2491	16.5053

Framework versions

• Transformers 4.44.1
• Pytorch 2.3.1+cu118
• Datasets 3.2.0
• Tokenizers 0.19.1