metadata

language:
  - vi
base_model: openai/whisper-small-vi-v2
tags:
  - generated_from_trainer
datasets:
  - vi_500/80k
metrics:
  - wer
model-index:
  - name: Whisper Small Vi - Anh Phuong
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: vi 500
          type: vi_500/80k
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 5.828968294497862

Whisper Small Vi - Anh Phuong

This model is a fine-tuned version of openai/whisper-small-vi-v2 on the vi 500 dataset. It achieves the following results on the evaluation set:

Loss: 0.1002
Wer: 5.8290

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: 4
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
0.1638	0.2	1000	0.1707	9.6824
0.1233	0.4	2000	0.1302	7.4792
0.1063	0.6	3000	0.1097	6.4330
0.0962	0.8	4000	0.1002	5.8290

Framework versions

Transformers 4.43.3
Pytorch 2.4.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1