namkyeong/whisper_8

openai/whisper-tiny

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

• Loss: 0.3738
• Cer: 13.4287

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
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 64
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 250000

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.5117	0.31	30000	0.4877	21.1183
0.4554	0.61	60000	0.4383	18.1652
0.4522	0.92	90000	0.4145	15.3446
0.4183	1.23	120000	0.4001	14.2250
0.402	1.53	150000	0.3913	13.6760
0.4031	1.84	180000	0.3830	14.3400
0.3735	2.15	210000	0.3766	14.6654
0.3829	2.46	240000	0.3738	13.4287

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1
• Datasets 2.15.0
• Tokenizers 0.15.0