restaurant_HSR_test

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

• Loss: 1.3461
• Wer: 50.0

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: 5
• training_steps: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	10.0	10	7.3374	133.3333
No log	20.0	20	2.1528	33.3333
6.4843	30.0	30	1.4666	16.6667
6.4843	40.0	40	1.3461	50.0

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.11.0+cu115
• Datasets 2.9.0
• Tokenizers 0.13.2