farsipal/whisper-md-el-intlv-xs

whisper-md-el-intlv-xs

This model is a fine-tuned version of openai/whisper-medium on interleaved mozilla-foundation/commonvoice110 (el) and the google/fleurs (elgr) datasets. It achieves the following results on the mozilla-foundation/commonvoice11_0 test evaluation set:

• —Loss: 0.4168
• —Wer: 11.3670

Model description

This model is trained over the two interleaved datasets in the Greek language. Testing used only the commonvoice11_0 (el) test split.

Intended uses & limitations

The model was trained for transcription in Greek

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 8e-06
• —trainbatchsize: 32
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —training_steps: 10000
• —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