nguyenloi/whisper_fine_tunning_2scx

Whisper Medium VI - Multi - Augmented

This model is a fine-tuned version of openai/whisper-medium on the following datasets:

• —mozilla-foundation/common_voice_11_0
• —google/fleurs
• —vivos

It achieves the following results on the evaluation set:

• —Loss: 0.3696
• —Wer: 16.6594
• —Cer: 7.7625

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 1e-05
• —trainbatchsize: 32
• —evalbatchsize: 16
• —seed: 42
• —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 1.13.1+cu117
• —Datasets 2.7.1.dev0
• —Tokenizers 0.13.2