whisper-small-hi2

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

• Loss: 0.2368
• Wer: 913.6858

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: 0.0001
• train_batch_size: 8
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1035	4.0	1000	0.2595	562.6750
0.0256	8.0	2000	0.2227	220.2177
0.0015	12.0	3000	0.2375	295.8009
0.0001	16.0	4000	0.2368	913.6858

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1