whisper_small_tw7

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: 3.7222
• Wer: 6.2899

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: 6.25e-06
• 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: linear
• lr_scheduler_warmup_steps: 800
• training_steps: 2400

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4744	30.77	400	3.5037	3.7269
0.0091	61.54	800	3.5131	8.7773
0.0002	92.31	1200	3.6276	6.3277
0.0001	123.08	1600	3.6844	6.2941
0.0001	153.85	2000	3.7112	5.9622
0.0001	184.62	2400	3.7222	6.2899

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3