luyotw/openfun-ivod-whisper-medium-common-11-626

Fine-tune 資訊

• 原始模型: openai/whisper-medium
• 使用音訊數量: 111244
• 使用音訊總長: 67.66 小時
• 音訊平均長度: 2.19 秒
• GPU: NVIDIA H100 PCIe x 1
• 訓練時間: 04:50:41
• 模型大小: 2.85 GB
• 訓練參數:
  • batch size: 20
  • eval batch size: 10
  • 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: 0.0197
• Wer: 75.1993

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: 20
• eval_batch_size: 10
• 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: 200
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0212	0.0719	400	0.0224	78.0550
0.0211	0.1438	800	0.0213	77.1936
0.0194	0.2157	1200	0.0205	75.9496
0.0192	0.2876	1600	0.0200	75.6781
0.018	0.3595	2000	0.0197	75.1993

Framework versions

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