ihanif/whisper-medium-ps

Whisper Medium Pashto

This model is a fine-tuned version of openai/whisper-medium on the google/fleurs ps_af dataset. It achieves the following results on the evaluation set:

• Loss: 1.2950
• Wer: 50.6432

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: 32
• eval_batch_size: 16
• 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: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0139	14.29	100	1.0302	50.1211
0.0011	28.57	200	1.2129	49.7806
0.0008	42.86	300	1.2581	50.3178
0.0007	57.14	400	1.2850	50.5524
0.0007	71.43	500	1.2950	50.6432

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2