metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - Chinese_english
metrics:
  - wer
model-index:
  - name: Whisper tiny Chinese
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Chinese English
          type: Chinese_english
          args: 'config: default, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 18.379666401906274

Whisper tiny Chinese

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

Loss: 0.5120
Wer: 18.3797

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: 2
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.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: 1500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	1.6667	500	0.4646	17.5060
0.0	3.3333	1000	0.5031	18.0937
0.0	5.0	1500	0.5120	18.3797

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1