Hugging Face's logo

razhan
/
whisper-small-ckb

Automatic Speech Recognition Transformers PyTorch TensorBoard Safetensors
Central Kurdish Kurdish
whisper whisper-event generated_from_trainer Eval Results Inference Endpoints
Model card Files Metrics Community
3
whisper-small-ckb / README.md
razhan's picture
razhan
Librarian Bot: Add base_model information to model (#2)
4c00ac4
preview code
|
raw history blame contribute delete
No virus
2.9 kB
metadata
language:
  - ckb
  - ku
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
  - google/fleurs
metrics:
  - wer
  - cer
base_model: openai/whisper-small
model-index:
  - name: Whisper Small Ckb - Razhan Hameed
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: ckb
          split: test
        metrics:
          - type: wer
            value: 33.2192952446117
            name: Wer
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: razhan/asosoft-speech
          type: razhan/asosoft-speech
          config: ckb
          split: test
        metrics:
          - type: wer
            value: 31.94
            name: WER
          - type: cer
            value: 5.65
            name: CER

Whisper Small Ckb - Razhan Hameed

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3825
  • Wer: 33.2193

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

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: 12000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1693 2.49 1000 0.2060 39.1265
0.0722 4.98 2000 0.2124 36.3173
0.0127 7.46 3000 0.2736 36.5568
0.008 9.95 4000 0.3131 35.7015
0.0032 12.44 5000 0.3434 35.3936
0.0028 14.93 6000 0.3453 35.9258
0.003 17.41 7000 0.3558 34.9565
0.0022 19.9 8000 0.3593 34.2722
0.0016 22.39 9000 0.3639 34.3369
0.0015 24.88 10000 0.3785 34.0062
0.0009 27.36 11000 0.3915 34.2951
0.0001 29.85 12000 0.3825 33.2193

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2