README.md

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: 66.14709443099274

Whisper Tiny Pashto

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

• Loss: 1.0195
• Wer: 66.1471

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: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 40
• training_steps: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5307	14.29	100	1.0195	66.1471
0.1225	28.57	200	1.1465	66.0185
0.0498	42.86	300	1.2300	66.0336

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2