metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - british_english_AE_fa
model-index:
  - name: Whisper tiny Chinese
    results: []

Whisper tiny British

This model is a fine-tuned version of openai/whisper-tiny on the British English 'AE' Phonemes dataset. It achieves the following results on the evaluation set:

eval_loss: 0.3636
eval_wer: 13.2631
eval_runtime: 140.0191
eval_samples_per_second: 3.392
eval_steps_per_second: 3.392
epoch: 2.5
step: 1500

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: 2
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 2000

Framework versions

Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1