metadata

base_model: openai/whisper-tiny
datasets:
  - fleurs
language:
  - th
library_name: transformers
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Tiny Thai Punctuation 5k - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: th_th
          split: None
          args: 'config: th split: test'
        metrics:
          - type: wer
            value: 123.48610781287105
            name: Wer

Whisper Tiny Thai Punctuation 5k - Chee Li

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

Loss: 0.7730
Wer: 123.4861

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
0.2888	5.2356	1000	0.6095	131.7739
0.0918	10.4712	2000	0.6100	119.5203
0.0229	15.7068	3000	0.6838	122.1325
0.0069	20.9424	4000	0.7521	121.0639
0.0049	26.1780	5000	0.7730	123.4861

Framework versions

Transformers 4.46.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.20.3