metadata
language:
- vi
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Vi - dtduy77
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: vi
split: test
args: 'config: vi, split: test'
metrics:
- name: Wer
type: wer
value: 59.5789011953065
Whisper Small Vi - dtduy77
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6917
- Wer: 59.5789
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 |
|---|---|---|---|---|
| 0.0218 | 5.7471 | 1000 | 0.5963 | 68.7246 |
| 0.0005 | 11.4943 | 2000 | 0.6530 | 62.8468 |
| 0.0003 | 17.2414 | 3000 | 0.6809 | 60.4014 |
| 0.0002 | 22.9885 | 4000 | 0.6917 | 59.5789 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1