CoolFace
Modelpublic

scinerd68/wav2vec2-large-xlsr-53-esperanto-esperanto-asr-augment-dynamic

sourceHugging Faceapache-2.0updated 10mo agoView on Hugging Face
0likes19downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

wav2vec2-large-xlsr-53-esperanto-esperanto-asr-augment-dynamic

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

  • —Loss: 0.2010
  • —Wer: 0.2699

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
  • —trainbatchsize: 4
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 8
  • —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 30
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.78860.13331000.63120.8321
0.48120.26672000.36940.7322
0.37730.43000.27790.6179
0.35270.53334000.21690.5091
0.32080.66675000.18290.4537
0.34760.86000.18610.4446
0.31210.93337000.17480.4226
0.3141.06678000.16950.4265
0.26131.29000.16480.4155
0.30941.333310000.16330.4153
0.25871.466711000.15650.3965
0.33071.612000.16210.3955
0.2891.733313000.16150.4014
0.27361.866714000.14710.3790
0.24892.015000.15600.3801
0.29562.133316000.15310.3809
0.24272.266717000.15680.3869
0.27562.418000.15590.3884
0.31542.533319000.15320.3921
0.25612.666720000.14770.3751
0.26022.821000.15550.3852
0.27812.933322000.15260.3759
0.22513.066723000.15250.3811
0.22123.224000.15540.3762
0.24773.333325000.14610.3654
0.22193.466726000.14890.3658
0.24493.627000.14320.3618
0.25593.733328000.15430.3763
0.2413.866729000.15100.3585
0.24784.030000.14360.3598
0.17254.133331000.14860.3585
0.22544.266732000.15480.3671
0.22434.433000.14650.3658
0.25844.533334000.14410.3596
0.22794.666735000.14580.3634
0.21274.836000.14700.3663
0.23324.933337000.14910.3571
0.19725.066738000.14870.3516
0.20815.239000.14530.3500
0.19875.333340000.14600.3577
0.22595.466741000.14790.3593
0.26365.642000.14630.3581
0.26215.733343000.14150.3432
0.18915.866744000.13870.3435
0.2056.045000.14590.3464
0.19686.133346000.14340.3470
0.20336.266747000.14250.3472
0.15566.448000.14830.3433
0.20436.533349000.15290.3525
0.17576.666750000.13780.3325
0.20316.851000.13950.3401
0.18956.933352000.14330.3420
0.1847.066753000.15560.3424
0.20427.254000.14100.3362
0.17427.333355000.14540.3460
0.17947.466756000.14550.3487
0.18647.657000.13730.3395
0.19027.733358000.14620.3422
0.19077.866759000.14370.3404
0.16058.060000.14640.3379
0.14948.133361000.14690.3297
0.19828.266762000.14540.3283
0.19848.463000.15250.3450
0.18138.533364000.14680.3353
0.16598.666765000.15000.3392
0.12718.866000.14120.3283
0.15868.933367000.14920.3334
0.13699.066768000.15640.3367
0.14199.269000.14860.3307
0.14239.333370000.16810.3378
0.12369.466771000.14600.3219
0.13369.672000.15010.3313
0.15919.733373000.15330.3339
0.17879.866774000.14270.3230
0.162110.075000.15900.3379
0.158910.133376000.15700.3296
0.144210.266777000.15010.3287
0.136410.478000.15680.3296
0.125210.533379000.15210.3258
0.147810.666780000.14790.3217
0.110310.881000.14640.3191
0.149510.933382000.15550.3316
0.120711.066783000.15590.3271
0.103611.284000.16790.3249
0.114211.333385000.17090.3255
0.122411.466786000.15420.3250
0.113511.687000.15290.3121
0.120411.733388000.15010.3136
0.126511.866789000.15690.3075
0.103512.090000.15160.3096
0.11812.133391000.15720.3148
0.124412.266792000.16320.3169
0.099212.493000.16780.3149
0.096112.533394000.17160.3232
0.131412.666795000.16700.3196
0.114912.896000.16400.3201
0.108512.933397000.17460.3124
0.11813.066798000.16090.3079
0.100813.299000.16670.3184
0.105113.3333100000.17930.3128
0.096913.4667101000.17520.3191
0.124213.6102000.16750.3107
0.103913.7333103000.16240.3165
0.095413.8667104000.16210.3062
0.122314.0105000.16210.3137
0.105214.1333106000.17130.3150
0.099514.2667107000.17510.3121
0.112814.4108000.17960.3096
0.091914.5333109000.17840.3049
0.093114.6667110000.18350.3099
0.106914.8111000.18560.3095
0.094414.9333112000.17810.3082
0.091515.0667113000.18660.3091
0.085115.2114000.18970.3071
0.074615.3333115000.18750.3054
0.082815.4667116000.18220.3084
0.107715.6117000.18080.3082
0.071915.7333118000.18600.3046
0.112115.8667119000.16740.3016
0.087316.0120000.16360.3024
0.069416.1333121000.17380.3029
0.100816.2667122000.17960.3058
0.081116.4123000.18660.3013
0.08116.5333124000.17810.3037
0.064716.6667125000.17110.2999
0.077516.8126000.17130.3003
0.06916.9333127000.18530.2977
0.077517.0667128000.19550.3029
0.07717.2129000.18620.3021
0.080217.3333130000.17590.3000
0.061517.4667131000.20720.3057
0.064717.6132000.17150.3044
0.070917.7333133000.16340.3031
0.097917.8667134000.18510.3012
0.067418.0135000.18860.3045
0.056218.1333136000.20090.3045
0.057118.2667137000.19800.3058
0.078218.4138000.19420.3059
0.054918.5333139000.18740.3028
0.060318.6667140000.18600.3020
0.072918.8141000.18140.2974
0.064618.9333142000.19160.3003
0.077319.0667143000.18400.3027
0.067219.2144000.19080.2977
0.071419.3333145000.19720.2963
0.06419.4667146000.18320.2920
0.058319.6147000.18580.3000
0.065119.7333148000.17780.3000
0.045319.8667149000.18910.2924
0.06720.0150000.19170.2912
0.048520.1333151000.18530.2908
0.06220.2667152000.19080.2877
0.048620.4153000.19920.2940
0.055120.5333154000.19380.2924
0.059820.6667155000.19480.2907
0.058620.8156000.20210.2898
0.056320.9333157000.19720.2921
0.053321.0667158000.19100.2900
0.063821.2159000.19700.2867
0.058221.3333160000.19610.2895
0.063421.4667161000.19200.2867
0.060521.6162000.18750.2889
0.052321.7333163000.18850.2864
0.051621.8667164000.19560.2877
0.078922.0165000.18340.2819
0.055822.1333166000.18620.2842
0.047122.2667167000.18680.2842
0.035222.4168000.19100.2842
0.04722.5333169000.17310.2852
0.041222.6667170000.18230.2839
0.072822.8171000.18630.2814
0.045622.9333172000.17890.2807
0.037823.0667173000.19470.2829
0.039423.2174000.19170.2804
0.067223.3333175000.18740.2824
0.041223.4667176000.19630.2836
0.055823.6177000.20260.2861
0.048423.7333178000.19760.2837
0.048823.8667179000.19360.2818
0.058424.0180000.18700.2831
0.051624.1333181000.19450.2811
0.065824.2667182000.19670.2860
0.043224.4183000.19860.2839
0.046324.5333184000.18750.2807
0.049224.6667185000.19770.2814
0.038924.8186000.20530.2785
0.035624.9333187000.20020.2793
0.048425.0667188000.19610.2789
0.026725.2189000.20640.2773
0.08525.3333190000.20730.2752
0.041925.4667191000.20800.2769
0.047425.6192000.21260.2785
0.038425.7333193000.20030.2770
0.027525.8667194000.19670.2769
0.02226.0195000.20110.2786
0.03826.1333196000.20260.2777
0.036826.2667197000.20370.2745
0.042926.4198000.20570.2748
0.037526.5333199000.19910.2770
0.045226.6667200000.19550.2741
0.051526.8201000.19850.2760
0.039826.9333202000.20280.2760
0.034327.0667203000.20040.2732
0.032427.2204000.20300.2729
0.043427.3333205000.20330.2724
0.037227.4667206000.20700.2731
0.040427.6207000.20130.2774
0.034927.7333208000.20440.2750
0.045927.8667209000.20530.2739
0.03828.0210000.19930.2732
0.03328.1333211000.19950.2703
0.036828.2667212000.19970.2716
0.05128.4213000.20000.2723
0.047628.5333214000.19800.2710
0.041628.6667215000.20170.2728
0.029428.8216000.20140.2728
0.025228.9333217000.20170.2723
0.045129.0667218000.19890.2722
0.034329.2219000.20070.2720
0.034229.3333220000.19910.2706
0.042229.4667221000.20020.2708
0.015629.6222000.20120.2706
0.051929.7333223000.20080.2707
0.051129.8667224000.20110.2700
0.034530.0225000.20100.2699

Framework versions

  • —Transformers 4.57.1
  • —Pytorch 2.9.0+cu126
  • —Datasets 4.0.0
  • —Tokenizers 0.22.1