thomas0104/whisper_medium_nan_tw

Whisper medium nan-tw

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 nan-tw dataset. It achieves the following results on the evaluation set:

• Loss: 0.9100
• Wer: 42.0709
• Cer: 22.3681

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.0568	5.0	1000	0.7769	48.2706	26.0890
0.0057	10.0	2000	0.8438	44.0722	23.9270
0.0041	15.01	3000	0.8740	42.8540	22.9554
0.0001	20.01	4000	0.9041	42.1797	22.5496
0.0001	25.01	5000	0.9100	42.0709	22.3681

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.8.0
• Tokenizers 0.13.2