whisper-large-english-TG

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

• Loss: 0.4494
• Wer: 18.0005

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
0.0452	2.6350	1000	0.3455	19.6915
0.0034	5.2701	2000	0.3999	17.8823
0.0005	7.9051	3000	0.4770	18.1438
0.0001	10.5402	4000	0.4494	18.0005

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1