Hugging Face's logo

linshoufan
/
linshoufan-whisper-small-nan-tw

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Min Nan Chinese
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
linshoufan-whisper-small-nan-tw / README.md
linshoufan's picture
linshoufan
End of training
5609b29 verified
preview code
|
raw
history blame
1.72 kB
metadata
language:
  - nan
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
model-index:
  - name: Whisper Small nan-tw - Taiwanese
    results: []

Whisper Small nan-tw - Taiwanese

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: 0.7966
  • Cer: 44.6503

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
0.329 2.99 1000 0.7453 48.6010
0.0121 5.99 2000 0.7780 46.0104
0.0013 8.98 3000 0.7884 44.5855
0.0006 11.98 4000 0.7966 44.6503

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2