metadata
language:
- vi
license: apache-2.0
base_model: openai/whisper-small
tags:
- leaderboards
- generated_from_trainer
datasets:
- vivos
metrics:
- wer
model-index:
- name: Whisper - Vivos
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Vivos
type: vivos
config: null
split: None
args: 'split: test'
metrics:
- name: Wer
type: wer
value: 54.85625485625486
Whisper - Vivos
This model is a fine-tuned version of openai/whisper-small on the Vivos dataset. It achieves the following results on the evaluation set:
- Loss: 0.2370
- Wer: 54.8563
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1265 | 1.37 | 1000 | 0.2178 | 35.8845 |
| 0.062 | 2.74 | 2000 | 0.2138 | 49.8446 |
| 0.0169 | 4.12 | 3000 | 0.2273 | 52.2922 |
| 0.012 | 5.49 | 4000 | 0.2370 | 54.8563 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.13.1
- Tokenizers 0.13.3