Hugging Face's logo

liuh6
/
whisper-tiny_to_Chinese_accent

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results
Model card Files Metrics Community
whisper-tiny_to_Chinese_accent / README.md
liuh6's picture
liuh6
End of training
f1a4bf6 verified
preview code
|
raw
history blame
1.48 kB
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
model-index:
  - name: Whisper tiny Chinese
    results: []

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:

  • eval_loss: 0.3483
  • eval_wer: 15.8380
  • eval_runtime: 183.8429
  • eval_samples_per_second: 3.421
  • eval_steps_per_second: 3.421
  • epoch: 0.6667
  • step: 200

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: 44
  • 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

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.6.0+cu124
  • Datasets 3.5.0
  • Tokenizers 0.21.1