whisper_AN_demo

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: 0.5163
• Wer Ortho: 34.7268
• Wer: 29.6857

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.6419	0.05	100	0.8019	31.6674	26.4281
0.2769	0.1	200	0.5559	32.3914	27.3457
0.2674	0.15	300	0.5354	39.1172	33.8151
0.2672	0.19	400	0.5247	34.6333	29.6628
0.2876	0.24	500	0.5163	34.7268	29.6857

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1