arun100/whisper-base-fa-2

Whisper Base Persian Iranian

This model is a fine-tuned version of arun100/whisper-base-fa-1 on the google/fleurs fa_ir dataset. It achieves the following results on the evaluation set:

• Loss: 0.5030
• Wer: 41.2338

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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
0.1284	86.0	1000	0.5030	41.2338
0.0179	173.0	2000	0.5767	41.6119
0.0074	260.0	3000	0.6171	41.4478
0.0047	347.0	4000	0.6419	42.1791
0.0039	434.0	5000	0.6517	41.9751

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.16.2.dev0
• Tokenizers 0.15.0