luyotw/openfun-ivod-whisper-large-v3-negotiation-11-32

Fine-tune 資訊

• 原始模型: openai/whisper-large-v3
• 使用音訊數量: 25457
• 使用音訊總長: 14.65 小時
• 音訊平均長度: 2.07 秒
• GPU: NVIDIA H100 PCIe x 1
• 訓練時間: 06:31:20
• 模型大小: 5.75 GB
• 訓練參數:
  • batch size: 8
  • eval batch size: 4
  • 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: 0.0206
• Wer: 76.6006

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: 8
• eval_batch_size: 4
• 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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.025	0.3142	1000	0.0233	80.6920
0.0216	0.6283	2000	0.0224	79.8761
0.0229	0.9425	3000	0.0214	77.8751
0.0158	1.2567	4000	0.0210	77.3391
0.0123	1.5708	5000	0.0206	76.6006

Framework versions

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