Hugging Face's logo

kul-speech-lab
/
whisper_medium_CGN

Automatic Speech Recognition
Transformers
whisper
whisper-event
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
whisper_medium_CGN / README.md
Jakob Poncelet
First model version
25e190f
preview code
|
raw history blame contribute delete
2.34 kB
metadata
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - kul-speech-lab/CGN
metrics:
  - wer
model-index:
  - name: Whisper Medium CGN
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: kul-speech-lab/CGN
          type: kul-speech-lab/CGN
          config: cgn-dev.py
          split: test
        metrics:
          - name: Wer
            type: wer
            value: 10.727751271110364

Whisper Medium CGN

This model is a fine-tuned version of openai/whisper-medium on the kul-speech-lab/CGN dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2639
  • Wer: 10.7278

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 64
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 15000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1116 1.01 1000 0.2978 15.2127
0.0786 2.03 2000 0.2842 13.4852
0.2042 3.04 3000 0.2656 13.3590
0.1183 4.05 4000 0.2667 12.6977
0.0584 6.01 5000 0.2604 12.0993
0.0126 7.02 6000 0.2776 12.1477
0.0837 8.04 7000 0.2541 11.9397
0.0229 9.05 8000 0.2663 11.3221
0.042 11.01 9000 0.2549 11.4863
0.0075 12.02 10000 0.2775 11.0780
0.008 13.03 11000 0.2499 10.9759
0.0739 14.05 12000 0.2308 10.9441
0.0379 16.01 13000 0.2423 10.7926
0.02 17.02 14000 0.2629 10.7699
0.0111 18.03 15000 0.2639 10.7278

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2

Whisper medium model finetuned on Flemish part of Corpus Gesproken Nederlands (CGN).