metadata

base_model: openai/whisper-tiny
datasets:
  - fleurs
language:
  - tr
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Tiny - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: tr_tr
          split: None
          args: 'config: tr split: test'
        metrics:
          - type: wer
            value: 38.612321095208465
            name: Wer

Whisper Tiny - 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: 0.6536
Wer: 38.6123

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
0.2876	5.5866	1000	0.5633	34.9642
0.0496	11.1732	2000	0.5952	33.5641
0.016	16.7598	3000	0.6390	36.2166
0.0099	22.3464	4000	0.6536	38.6123

Framework versions

Transformers 4.44.0
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1