whisper-small-hi / README.md
Hawk91's picture
update model card README.md
a161a14
metadata
language:
  - hi
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
metrics:
  - wer
model-index:
  - name: Whisper Small Hi - Hawk
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 13
          type: mozilla-foundation/common_voice_13_0
          config: hi
          split: test
          args: hi
        metrics:
          - name: Wer
            type: wer
            value: 35.53475278714895

Whisper Small Hi - Hawk

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8294
  • Wer Ortho: 58.7561
  • Wer: 35.5348

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: 4
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 50

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.9225 0.03 50 0.8294 58.7561 35.5348

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3