whisper-small-cntt2

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: 0.6061
• Wer: 64.3143
• Cer: 51.0104

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: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.0207	7.19	1000	0.4723	76.4951	61.2694
0.0017	14.39	2000	0.5593	69.3438	55.3014
0.0008	21.58	3000	0.5938	67.1198	53.9426
0.0006	28.78	4000	0.6061	64.3143	51.0104

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3