liqi03/whisper-large-v3-fa-fleurs

Whisper Large V3 fa fleurs- Chee Li

This model is a fine-tuned version of openai/whisper-large-v3 on the Google Fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.1409
• Wer: 33.0741

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-06
• 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: 125
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1605	1.1521	250	0.1698	16.5640
0.1076	2.3041	500	0.1445	26.3351
0.0938	3.4562	750	0.1406	34.2381
0.088	4.6083	1000	0.1409	33.0741

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1