metadata
language:
- vi
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
base_model: openai/whisper-small
model-index:
- name: Whisper Small Vietnamese
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: mozilla-foundation/common_voice_11_0 vi
type: mozilla-foundation/common_voice_11_0
config: vi
split: None
metrics:
- type: wer
value: 34.21715788320368
name: Wer
Whisper Small Vietnamese
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 vi dataset. It achieves the following results on the evaluation set:
- Loss: 0.9921
- Wer: 34.2172
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: 64
- eval_batch_size: 32
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0002 | 124.0 | 1000 | 0.7998 | 21.7706 |
| 0.0001 | 249.0 | 2000 | 0.8833 | 28.9690 |
| 0.0 | 374.0 | 3000 | 0.9382 | 30.8206 |
| 0.0 | 499.0 | 4000 | 0.9754 | 34.4363 |
| 0.0 | 624.0 | 5000 | 0.9921 | 34.2172 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.7.1
- Tokenizers 0.13.2