Hugging Face's logo

Quiglee2
/
whisper-tiny-chinese-ft

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community

Whisper tiny Chinese accent

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: 0.3072
  • Wer: 13.3439

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_FUSED 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: 2000

Training results

Training Loss Epoch Step Validation Loss Wer
0.1224 1.2837 1000 0.3158 14.2971
0.0590 2.5674 2000 0.3072 13.3439

Framework versions

  • Transformers 5.23.0.dev0
  • Pytorch 2.11.0+cu130
  • Datasets 5.1.0
  • Tokenizers 0.23.3
Downloads last month
22
Safetensors
Model size
37.8M params
Tensor type
F32
·
Inference Providers NEW
Automatic Speech Recognition
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Quiglee2/whisper-tiny-chinese-ft

Base model

openai/whisper-tiny
Finetuned
(2070)
this model

Dataset used to train Quiglee2/whisper-tiny-chinese-ft

Evaluation results