metadata
language:
- vi
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
base_model: openai/whisper-small
model-index:
- name: Whisper Small Mnong
results: []
Whisper Small Mnong
This model is a fine-tuned version of openai/whisper-small on the MnongAudio dataset. It achieves the following results on the evaluation set:
- Loss: 1.2467
- Wer: 62.1199
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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2715 | 5.92 | 1000 | 1.1361 | 69.9392 |
| 0.0052 | 11.83 | 2000 | 1.2203 | 70.9818 |
| 0.0005 | 17.75 | 3000 | 1.2350 | 59.6872 |
| 0.0004 | 23.67 | 4000 | 1.2467 | 62.1199 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2