luyotw/openfun-ivod-whisper-medium-common-10-626

Fine-tune 資訊

• 原始模型: openai/whisper-medium
• 使用音訊數量: 118922
• 使用音訊總長: 70.50 小時
• 音訊平均長度: 2.13 秒
• GPU: NVIDIA H100 PCIe x 1
• 訓練時間: 03:34:57
• 模型大小: 2.85 GB
• 訓練參數:
  • batch size: 16
  • eval batch size: 8
  • gradient checkpointing: False
  • fp16: False
  • bf16: True

---

Fine-tuned Whisper model for Legislative Yuan of Taiwan

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

• Loss: 0.0192
• Wer: 73.8276

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: 250
• training_steps: 2500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0227	0.0673	500	0.0218	76.7862
0.0222	0.1345	1000	0.0209	75.9748
0.0217	0.2018	1500	0.0201	75.5901
0.0206	0.2691	2000	0.0195	74.2298
0.0187	0.3363	2500	0.0192	73.8276

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1
• Datasets 3.5.0
• Tokenizers 0.21.1