Fine-tune 資訊

  • 原始模型: openai/whisper-large-v3
  • 使用音訊數量: 22318
  • 使用音訊總長: 11.74 小時
  • 音訊平均長度: 1.89 秒
  • GPU: NVIDIA H100 PCIe x 1
  • 訓練時間: 02:50:20
  • 模型大小: 5.75 GB
  • 訓練參數:
    • batch size: 80
    • eval batch size: 40
    • gradient checkpointing: True
    • fp16: False
    • bf16: True

Fine-tuned Whisper model for Legislative Yuan of Taiwan

This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0188
  • Wer: 72.0212

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: 80
  • eval_batch_size: 40
  • 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: 50
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss Wer
0.0227 0.3584 100 0.0204 74.5344
0.0188 0.7168 200 0.0194 72.9145
0.0148 1.0753 300 0.0190 72.1575
0.0157 1.4337 400 0.0191 72.0969
0.0149 1.7921 500 0.0188 72.0212

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.5.1
  • Datasets 3.5.0
  • Tokenizers 0.21.1
Downloads last month
3
Safetensors
Model size
1.54B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for luyotw/openfun-ivod-whisper-large-v3-LaiShiBao-11-124

Finetuned
(599)
this model