seanghay/whisper-small-khmer-unspaced

<!-- 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 Small Khmer - Seanghay Yath

This model is a fine-tuned version of openai/whisper-small on the Google FLEURS & OpenSLR dataset. It achieves the following results on the evaluation set:

• —Loss: 0.4484
• —Wer: 1.0704

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 6.25e-06
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 800
• —training_steps: 4000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.28.0.dev0
• —Pytorch 1.12.1
• —Datasets 2.11.1.dev0
• —Tokenizers 0.13.3