whisper-small-hi3

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: 1.2182
• Wer: 267.2819

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
0.0599	8.0	1000	0.9703	364.7651
0.0093	16.0	2000	1.2675	385.5705
0.0001	24.0	3000	1.2238	270.8054
0.0	32.0	4000	1.2182	267.2819

Framework versions

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