Hugging Face's logo

momo103197
/
whisper-small-zh-TW

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-zh-TW / README.md
momo103197's picture
momo103197
End of training
8487301 verified
preview code
|
raw
history blame contribute delete
1.61 kB
metadata
library_name: transformers
language:
  - hi
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: Whisper Small zh-TW - Fine-tune
    results: []

Whisper Small zh-TW - Fine-tune

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1875
  • Cer: 9.7986

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: Use 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: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
0.0836 1.4184 1000 0.1875 9.7986

Framework versions

  • Transformers 4.48.3
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0