whisper-tiny-ps / README.md
ihanif's picture
update model card README.md
18069ce
|
raw
history blame
1.82 kB
metadata
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Tiny Pashto
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: google/fleurs ps_af
          type: google/fleurs
          config: ps_af
          split: test
          args: ps_af
        metrics:
          - name: Wer
            type: wer
            value: 273.23698547215497

Whisper Tiny Pashto

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

  • Loss: 3.4900
  • Wer: 273.2370

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: 3e-07
  • 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: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.14 1 3.4900 273.2370
No log 0.29 2 3.4900 273.2370

Framework versions

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