whisper_small.hi_lora

This model is a fine-tuned version of openai/whisper-small on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4588
• Wer: 52.1713

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4177	2.44	1000	0.5055	59.4430
0.3887	4.89	2000	0.4759	52.9544
0.3595	7.33	3000	0.4660	52.4634
0.3643	9.78	4000	0.4598	52.2221
0.3556	12.22	5000	0.4588	52.1713

Framework versions

• PEFT 0.10.0
• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2