farsipal/whisper-sm-el-intlv-xs

Whisper small (Greek) Trained on Interleaved Datasets

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

• —Loss: 0.4741
• —Wer: 20.0687

Model description

The model was developed during the Whisper Fine-Tuning Event in December 2022. More details on the model can be found in the original paper

Intended uses & limitations

The model is fine-tuned for transcription in the Greek language.

Training and evaluation data

This model was trained by interleaving the training and evaluation splits from two different datasets:

• —mozilla-foundation/commonvoice11_0 (el)
• —google/fleurs (el_gr)

Training procedure

The python script used is a modified version of the script provided by Hugging Face and can be found here

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 1e-05
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —training_steps: 5000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.26.0.dev0
• —Pytorch 1.13.0
• —Datasets 2.7.1.dev0
• —Tokenizers 0.12.1