metadata
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- tobiolatunji/afrispeech-200
model-index:
- name: Whisper Small En - Mpe_Lukhele
results: []
Whisper Small En - Mpendulo_Lukhele
This model is a fine-tuned version of openai/whisper-small on the AfriSpeech dataset. It achieves the following results on the evaluation set:
- eval_loss: 3.6218
- eval_wer: 48.2933
- eval_runtime: 1524.348
- eval_samples_per_second: 1.968
- eval_steps_per_second: 0.246
- step: 0
Model description
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: 8
- 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: 8
- training_steps: 10
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1