You can deploy this model and start earning money today!

Ganaa0614/
wav2vec2-large-xlsr-53-mongolian_ver_0.1

Name: wav2vec2-large-xlsr-53-mongolian_ver_0.1
Availability: InStock

Views

No views yet

wav2vec2-large-xlsr-53-mongolian_ver_0.1

This model is a fine-tuned version of tugstugi/wav2vec2-large-xlsr-53-mongolian on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1500
num_epochs: 60
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
16.3521	1.5697	400	3.2197	1.0
5.8125	3.1375	800	1.9820	0.9964
1.8715	4.7073	1200	0.7084	0.4978
0.8441	6.2750	1600	0.6001	0.4413
0.5866	7.8448	2000	0.5668	0.4266
0.4666	9.4126	2400	0.5660	0.4230
0.4026	10.9823	2800	0.5802	0.4157
0.3423	12.5501	3200	0.5952	0.4091
0.3171	14.1179	3600	0.6109	0.4094
0.3003	15.6876	4000	0.6276	0.4108
0.2688	17.2554	4400	0.6178	0.4022
0.2670	18.8251	4800	0.6249	0.4004
0.2471	20.3929	5200	0.6471	0.4037
0.2364	21.9627	5600	0.6304	0.3985
0.2189	23.5305	6000	0.6848	0.4036
0.2185	25.0982	6400	0.6442	0.3947
0.2064	26.6680	6800	0.6942	0.3990
0.2005	28.2358	7200	0.6741	0.3958
0.1924	29.8055	7600	0.6728	0.3923
0.1895	31.3733	8000	0.6950	0.3976
0.1801	32.9430	8400	0.7088	0.4005
0.1766	34.5108	8800	0.7246	0.3985
0.1755	36.0786	9200	0.7112	0.3931
0.1748	37.6483	9600	0.7215	0.3924
0.1650	39.2161	10000	0.7323	0.3909
0.1625	40.7859	10400	0.7199	0.3894
0.1619	42.3536	10800	0.7179	0.3920
0.1545	43.9234	11200	0.7358	0.3902
0.1478	45.4912	11600	0.7347	0.3862
0.1441	47.0589	12000	0.7210	0.3898
0.1459	48.6287	12400	0.7247	0.3867
0.1444	50.1965	12800	0.7422	0.3859
0.1430	51.7662	13200	0.7532	0.3856
0.1415	53.3340	13600	0.7531	0.3890
0.1435	54.9037	14000	0.7485	0.3870
0.1369	56.4715	14400	0.7421	0.3856
0.1377	58.0393	14800	0.7417	0.3865
0.1344	59.6090	15200	0.7443	0.3846