christoph-sl

This model is a fine-tuned version of openai/whisper-large on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3313
• Wer: 20.0641

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0153	6.08	1000	0.2795	26.4607
0.0013	12.16	2000	0.3083	22.2352
0.0001	18.24	3000	0.3251	21.5066
0.0001	24.32	4000	0.3313	20.0641

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2