ihanif/whisper-base-pashto

Whisper Tiny Pashto

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

• Loss: 1.0742
• Wer: 69.6126

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: 500
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.8225	14.29	100	1.7608	105.3193
0.7281	28.57	200	1.0742	69.6126
0.2329	42.86	300	1.1192	67.0248
0.0247	57.14	400	1.3495	66.3741
0.0057	71.43	500	1.5055	67.2896

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2