metadata
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-large-v2.vi2
results: []
datasets:
- google/fleurs
language:
- vi
pipeline_tag: automatic-speech-recognition
whisper-large-v2.vi2
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3148
- Wer: 13.9211
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: 250
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0284 | 2.66 | 500 | 0.2743 | 21.3778 |
| 0.0047 | 5.32 | 1000 | 0.2707 | 16.1299 |
| 0.0007 | 7.98 | 1500 | 0.2929 | 12.4846 |
| 0.0004 | 10.64 | 2000 | 0.3040 | 13.3418 |
| 0.0003 | 13.3 | 2500 | 0.3125 | 13.9983 |
| 0.0003 | 15.96 | 3000 | 0.3148 | 13.9211 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1