salmon-whisper-large-smj-lr7e-5

This model is a fine-tuned version of openai/whisper-large-v2 on the NbAiLab/salmon-asr-smj dataset.

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: 7e-05
• lr_scheduler_type: linear
• per_device_train_batch_size: 6
• total_train_batch_size_per_node: 48
• total_train_batch_size: 48
• total_optimization_steps: 100,000
• starting_optimization_step: None
• finishing_optimization_step: 100,000
• num_train_dataset_workers: 32
• num_hosts: 1
• total_num_training_examples: 4,800,000
• steps_per_epoch: 385
• num_beams: None
• weight_decay: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.98
• adam_epsilon: 1e-06
• dropout: True
• bpe_dropout_probability: 0.2
• activation_dropout_probability: 0.1

Training results

step	validation_loss	train_loss	validation_wer	validation_cer	validation_exact_wer	validation_exact_cer
0	4.2254	4.7016	112.7660	59.8700	108.1117	62.0594
10000	0.8352	0.3801	18.0851	5.5037	22.2074	6.0546
20000	1.1701	0.2580	15.2926	5.0569	17.8191	5.4770
30000	1.0861	0.2306	14.4947	4.6304	17.2872	4.9393
40000	1.0137	0.2168	14.2287	4.3461	16.7553	4.6206
50000	1.1032	0.2313	13.6968	3.8993	16.0904	4.1625
60000	1.2158	0.2121	13.6968	4.2648	16.0904	4.5808
70000	1.1595	0.2567	12.3670	3.7977	14.7606	4.1028
80000	1.1889	0.2420	12.5	4.0008	14.7606	4.2621
90000	1.1761	0.2039	12.6330	4.0211	14.8936	4.3218

Framework versions

• Transformers 4.35.0
• Datasets 2.14.6
• Tokenizers 0.14.1