Hugging Face's logo

jun-han
/
whisper-small-zh-TW

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Chinese
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-zh-TW / README.md
jun-han's picture
jun-han
End of training
ef1c984 verified
preview code
|
raw history blame contribute delete
No virus
1.68 kB
metadata
language:
  - zh
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
model-index:
  - name: Wisper-Small-zh-TW
    results: []

Wisper-Small-zh-TW

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3084
  • Cer: 15.6339

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 Cer
0.6123 1.3245 1000 0.6134 33.7535
0.1688 2.6490 2000 0.3170 17.2558
0.0472 3.9735 3000 0.3022 15.9905
0.01 5.2980 4000 0.3084 15.6339

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1