yesj1234/xlsr_enko_exp2

en-xlsr

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the ./SAMPLE_SPEECH.PY - NA dataset. It achieves the following results on the evaluation set:

• Loss: 0.5356
• Cer: 0.0853
• Wer: 0.1884

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: 0.0003
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
0.7055	2.79	600	0.4911	0.1304	0.3308
0.3761	5.58	1200	0.3984	0.1053	0.2533
0.278	8.37	1800	0.4070	0.1024	0.2445
0.2196	11.16	2400	0.4033	0.0974	0.2243
0.1842	13.95	3000	0.4270	0.0928	0.2106
0.1533	16.74	3600	0.4582	0.0916	0.2071
0.1257	19.53	4200	0.4685	0.0901	0.2001
0.1071	22.33	4800	0.5088	0.0878	0.1965
0.0967	25.12	5400	0.5224	0.0872	0.1913
0.0839	27.91	6000	0.5379	0.0860	0.1885

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1