whisper-tiny-hi / README.md
amitkayal's picture
update model card README.md
082da27
|
raw
history blame
2.03 kB
metadata
language:
  - hi
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: WhsprTiny-hi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: hi
          split: test
          args: hi
        metrics:
          - name: Wer
            type: wer
            value: 43.83526309755818

WhsprTiny-hi

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

  • Loss: 0.9060
  • Wer: 43.8353

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: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 400
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2265 3.04 1000 0.5764 43.5028
0.12 7.02 2000 0.6292 42.1271
0.0375 10.05 3000 0.7510 43.5229
0.0119 14.04 4000 0.8505 43.6203
0.0094 18.02 5000 0.9060 43.8353

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.10.0
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2