ihanif/whisper-large-pashto

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Whisper Large Pashto

This model is a fine-tuned version of openai/whisper-large-v2 on the google/fleurs ps_af dataset. It achieves the following results on the evaluation set:

• —Loss: 0.8623
• —Wer: 54.0685

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: 3e-07
• —trainbatchsize: 8
• —evalbatchsize: 4
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 50
• —training_steps: 700
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

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