Whisper large-v3 Bisyllabic Jyutping

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

• eval_loss: 0.2668
• eval_wer: 31.7361
• eval_runtime: 1403.0426
• eval_samples_per_second: 0.513
• eval_steps_per_second: 0.032
• epoch: 0.04
• step: 400

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 400
• training_steps: 2400

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0
• Datasets 2.14.5
• Tokenizers 0.15.1