Hugging Face's logo

ZhihCheng
/
whisper-base-zh

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Chinese
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-base-zh / README.md
ZhihCheng's picture
ZhihCheng
End of training
6cd73fa verified
preview code
|
raw history blame contribute delete
No virus
1.63 kB
metadata
language:
  - zh
base_model: ZhihCheng/whisper-base-zh
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper base ZH
    results: []

Whisper base ZH

This model is a fine-tuned version of ZhihCheng/whisper-base-zh on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2200
  • Wer: 44.8955

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
0.1704 0.27 1000 0.2787 51.6077
0.1479 0.54 2000 0.2480 48.4124
0.1145 0.81 3000 0.2289 46.1415
0.076 1.08 4000 0.2200 44.8955

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.2.0a0+6a974be
  • Datasets 2.16.1
  • Tokenizers 0.15.1