metadata

language:
  - vi
base_model: openai/whisper-small-vi-v2
tags:
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Small Vi - Anh Phuong
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Google fleurs
          type: google/fleurs
          config: vi_vn
          split: None
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 14.430800123571208

Whisper Small Vi - Anh Phuong

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

Loss: 0.4633
Wer: 14.4308

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: 6000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0133	4.7619	1000	0.3913	15.3383
0.0009	9.5238	2000	0.4180	14.3227
0.0006	14.2857	3000	0.4382	14.6162
0.0003	19.0476	4000	0.4496	14.4269
0.0002	23.8095	5000	0.4594	14.4578
0.0002	28.5714	6000	0.4633	14.4308

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1