masapasa/xls-r-300m-sv-cv8

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - SV-SE dataset. It achieves the following results on the evaluation set:

• Loss: 2.3347
• Wer: 1.0286

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: 7.5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 20
• num_epochs: 5.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
10.7838	0.01	5	14.5035	1.0
13.0582	0.03	10	13.6658	1.0
7.3034	0.04	15	9.7898	1.0
6.1847	0.05	20	6.9148	1.0
5.3371	0.07	25	5.3661	1.0
4.4274	0.08	30	4.6945	1.0
4.0918	0.1	35	4.3172	1.0
4.1734	0.11	40	4.0759	1.0
3.7332	0.12	45	3.9039	1.0
3.6871	0.14	50	3.7777	1.0
3.4428	0.15	55	3.6718	1.0
3.5514	0.16	60	3.5947	1.0
3.4307	0.18	65	3.5144	1.0
3.4102	0.19	70	3.4432	1.0
3.4964	0.21	75	3.3890	1.0
3.3936	0.22	80	3.3467	1.0
3.3051	0.23	85	3.3102	1.0
3.278	0.25	90	3.2801	1.0
3.2223	0.26	95	3.2440	1.0
3.1888	0.27	100	3.2900	1.0
3.218	0.29	105	3.2627	1.0
3.1308	0.3	110	3.2152	1.0
3.109	0.31	115	3.1686	1.0
3.1188	0.33	120	3.1734	1.0
3.1132	0.34	125	3.1431	1.0
3.0667	0.36	130	3.1686	1.0
3.1167	0.37	135	3.1885	1.0
3.0592	0.38	140	3.1100	1.0
3.0531	0.4	145	3.1149	1.0
3.1224	0.41	150	3.1205	1.0
3.0651	0.42	155	3.1101	1.0
3.0077	0.44	160	3.0980	1.0
3.0027	0.45	165	3.1132	1.0
3.0423	0.47	170	3.0886	1.0
3.0462	0.48	175	3.0865	1.0
3.0701	0.49	180	3.0863	1.0
3.0871	0.51	185	3.0825	1.0
3.0585	0.52	190	3.0720	1.0
3.0274	0.53	195	3.0736	1.0
3.0983	0.55	200	3.0658	1.0
3.0538	0.56	205	3.1241	1.0
3.0862	0.57	210	3.0573	1.0
3.0041	0.59	215	3.0608	1.0
3.027	0.6	220	3.0614	1.0
2.9916	0.62	225	3.0527	1.0
3.0157	0.63	230	3.0514	1.0
3.0429	0.64	235	3.0391	1.0
2.999	0.66	240	3.0462	1.0
3.0053	0.67	245	3.0438	1.0
2.9812	0.68	250	3.0447	1.0
3.0062	0.7	255	3.0660	1.0
3.0045	0.71	260	3.0103	1.0
2.9684	0.73	265	3.0106	1.0
2.9885	0.74	270	3.0014	1.0
3.0062	0.75	275	2.9885	1.0
2.9736	0.77	280	3.0330	1.0
2.9766	0.78	285	2.9910	1.0
2.9545	0.79	290	2.9972	1.0
2.9936	0.81	295	2.9872	1.0
3.0832	0.82	300	2.9978	1.0
2.974	0.83	305	2.9978	1.0
2.9846	0.85	310	2.9849	1.0
2.9554	0.86	315	2.9810	1.0
2.9524	0.88	320	2.9731	1.0
2.9426	0.89	325	2.9824	1.0
2.9416	0.9	330	2.9731	1.0
2.9705	0.92	335	2.9830	1.0
2.9502	0.93	340	2.9713	1.0
2.9393	0.94	345	2.9790	1.0
2.9336	0.96	350	2.9684	1.0
2.9542	0.97	355	2.9689	1.0
2.9408	0.98	360	2.9556	1.0
2.9544	1.0	365	2.9563	1.0
2.9187	1.01	370	2.9624	1.0
2.9935	1.03	375	2.9500	1.0
2.9803	1.04	380	2.9558	1.0
2.9867	1.05	385	2.9473	1.0
2.8925	1.07	390	2.9444	1.0
2.9633	1.08	395	2.9490	1.0
2.9191	1.1	400	2.9362	1.0
2.9081	1.11	405	2.9394	1.0
2.9381	1.12	410	2.9846	1.0
2.9271	1.14	415	2.9638	1.0
2.959	1.15	420	2.9835	1.0
2.9486	1.16	425	2.9361	1.0
2.9246	1.18	430	2.9615	1.0
2.923	1.19	435	2.9313	1.0
2.8908	1.21	440	2.9362	1.0
2.8976	1.22	445	2.9224	1.0
2.9278	1.23	450	2.9276	1.0
2.8429	1.25	455	2.9299	1.0
2.867	1.26	460	2.9258	1.0
2.9734	1.27	465	2.9281	1.0000
2.934	1.29	470	2.9229	1.0
2.9521	1.3	475	2.9134	1.0
2.9098	1.31	480	2.9051	0.9993
2.9112	1.33	485	2.9028	0.9999
2.8799	1.34	490	2.9101	0.9986
2.857	1.36	495	2.9005	0.9992
2.8525	1.37	500	2.8937	1.0
2.8682	1.38	505	2.8904	1.0000
2.8899	1.4	510	2.8914	0.9964
2.7475	1.41	515	2.8842	0.9950
2.9263	1.42	520	2.8852	0.9972
2.8603	1.44	525	2.8762	0.9966
2.864	1.45	530	2.8680	0.9978
2.8632	1.47	535	2.8602	0.9964
2.9289	1.48	540	2.8584	0.9952
2.8689	1.49	545	2.8587	0.9956
2.8304	1.51	550	2.8511	0.9993
2.8024	1.52	555	2.8460	1.0
2.7649	1.53	560	2.8460	1.0000
2.8756	1.55	565	2.8348	0.9987
2.8808	1.56	570	2.8539	0.9993
2.9027	1.57	575	2.8282	0.9975
2.8586	1.59	580	2.8288	0.9976
2.8193	1.6	585	2.8101	1.0051
2.811	1.62	590	2.7965	1.0014
2.7332	1.63	595	2.7884	1.0026
2.7717	1.64	600	2.7883	1.0060
2.6901	1.66	605	2.7801	0.9974
2.6905	1.67	610	2.8113	0.9968
2.7442	1.68	615	2.8113	1.0007
2.8431	1.7	620	2.8152	1.0343
2.8028	1.71	625	2.7790	1.0250
2.7151	1.73	630	2.7653	1.0287
2.7405	1.74	635	2.7714	1.1303
2.7566	1.75	640	2.7488	1.0312
2.7337	1.77	645	2.7498	1.0176
2.7486	1.78	650	2.7496	1.0760
2.6918	1.79	655	2.7391	1.0353
2.7142	1.81	660	2.7500	1.0283
2.7057	1.82	665	2.7612	1.0127
2.8348	1.83	670	2.7441	1.0056
2.705	1.85	675	2.7473	1.0519
2.7547	1.86	680	2.7216	1.0218
2.7045	1.88	685	2.7261	1.1414
2.7121	1.89	690	2.7223	1.0287
2.6877	1.9	695	2.7283	1.0274
2.6879	1.92	700	2.7451	1.1322
2.6958	1.93	705	2.7166	1.0364
2.6692	1.94	710	2.7148	1.0074
2.5786	1.96	715	2.7101	1.0504
2.6919	1.97	720	2.6963	1.0454
2.7256	1.98	725	2.7201	1.0349
2.6507	2.0	730	2.7099	1.1339
2.7833	2.01	735	2.7111	1.0124
2.7521	2.03	740	2.7024	1.0275
2.6732	2.04	745	2.7058	1.0647
2.719	2.05	750	2.7200	1.0211
2.701	2.07	755	2.7024	1.0808
2.6444	2.08	760	2.6813	1.0582
2.5592	2.1	765	2.6783	1.1010
2.6444	2.11	770	2.6707	1.0946
2.6944	2.12	775	2.7012	1.1315
2.6733	2.14	780	2.7072	1.1144
2.6998	2.15	785	2.7132	1.0206
2.796	2.16	790	2.7076	1.1262
2.6881	2.18	795	2.6953	1.0841
2.7382	2.19	800	2.6605	1.1234
2.5814	2.21	805	2.6814	1.1865
2.6695	2.22	810	2.6531	1.0985
2.6415	2.23	815	2.6590	1.0804
2.646	2.25	820	2.6514	1.0853
2.6028	2.26	825	2.6723	1.1411
2.6429	2.27	830	2.6729	1.0395
2.6736	2.29	835	2.7039	1.0355
2.6959	2.3	840	2.6510	1.0414
2.6426	2.31	845	2.6660	1.1591
2.7152	2.33	850	2.6361	1.0276
2.7148	2.34	855	2.6723	1.2461
2.6336	2.36	860	2.6332	1.0310
2.665	2.37	865	2.6365	1.1312
2.5607	2.38	870	2.6344	1.1301
2.5614	2.4	875	2.6437	1.1513
2.4899	2.41	880	2.6418	1.1532
2.6794	2.42	885	2.6403	1.0272
2.6814	2.44	890	2.6420	1.1323
2.6614	2.45	895	2.6183	1.0525
2.6629	2.47	900	2.6414	1.1569
2.6166	2.48	905	2.6167	1.0265
2.6374	2.49	910	2.6299	1.1720
2.6035	2.51	915	2.6139	1.1565
2.595	2.52	920	2.6126	1.0557
2.6416	2.53	925	2.6190	1.0414
2.6785	2.55	930	2.6352	1.0289
2.6986	2.56	935	2.6268	1.0077
2.6145	2.57	940	2.6166	1.0445
2.6961	2.59	945	2.6142	1.0185
2.6852	2.6	950	2.6072	1.0122
2.5792	2.62	955	2.6078	1.1165
2.6118	2.63	960	2.6177	1.1210
2.5472	2.64	965	2.6126	1.0044
2.577	2.66	970	2.6051	1.0881
2.5602	2.67	975	2.5992	1.0178
2.695	2.68	980	2.6023	1.0248
2.7017	2.7	985	2.6190	1.0041
2.6327	2.71	990	2.6024	1.0142
2.6193	2.73	995	2.5897	1.0148
2.5939	2.74	1000	2.5900	1.0329
2.5477	2.75	1005	2.5971	1.0338
2.6089	2.77	1010	2.5969	1.0064
2.5625	2.78	1015	2.5899	1.0648
2.5745	2.79	1020	2.5861	1.0627
2.5702	2.81	1025	2.5923	1.0526
2.645	2.82	1030	2.6053	1.0199
2.6869	2.83	1035	2.6227	1.0011
2.6678	2.85	1040	2.6094	1.0179
2.6787	2.86	1045	2.5978	1.0028
2.6246	2.88	1050	2.5965	1.0093
2.5676	2.89	1055	2.5927	1.0627
2.6773	2.9	1060	2.5907	1.0817
2.6114	2.92	1065	2.5932	1.1013
2.6227	2.93	1070	2.5840	1.0402
2.594	2.94	1075	2.5997	1.1371
2.751	2.96	1080	2.5909	1.0972
2.6366	2.97	1085	2.6081	1.0598
2.577	2.98	1090	2.5915	1.0410
2.579	3.0	1095	2.5953	1.1433
2.6706	3.01	1100	2.5913	1.0456
2.6161	3.03	1105	2.6079	1.1009
2.6397	3.04	1110	2.5951	1.1771
2.6246	3.05	1115	2.5730	1.0299
2.5637	3.07	1120	2.5622	1.0848
2.5692	3.08	1125	2.5561	1.1472
2.5948	3.1	1130	2.5568	1.0802
2.5372	3.11	1135	2.5638	1.1261
2.4995	3.12	1140	2.5727	1.1395
2.6304	3.14	1145	2.5671	1.0259
2.6395	3.15	1150	2.5778	1.0212
2.6127	3.16	1155	2.5609	1.0457
2.5919	3.18	1160	2.5604	1.0902
2.6111	3.19	1165	2.5463	1.0014
2.5971	3.21	1170	2.5429	1.0022
2.5887	3.22	1175	2.5394	1.0412
2.5644	3.23	1180	2.5342	1.0469
2.4805	3.25	1185	2.6066	1.2668
2.5324	3.26	1190	2.5395	1.0234
2.5491	3.27	1195	2.5431	1.0644
2.6302	3.29	1200	2.5558	1.0680
2.6139	3.3	1205	2.5711	1.0565
2.5607	3.31	1210	2.5635	1.0415
2.6535	3.33	1215	2.5505	1.0613
2.6129	3.34	1220	2.5403	1.0724
2.5157	3.36	1225	2.5294	1.0585
2.551	3.37	1230	2.5242	1.1599
2.5527	3.38	1235	2.5474	1.2327
2.4964	3.4	1240	2.5244	1.0857
2.5781	3.41	1245	2.5299	1.0470
2.6143	3.42	1250	2.5313	1.0019
2.6566	3.44	1255	2.5431	1.0488
2.5373	3.45	1260	2.5281	1.0901
2.6597	3.47	1265	2.5300	1.0610
2.5457	3.48	1270	2.5130	1.0420
2.5632	3.49	1275	2.5306	1.1418
2.5267	3.51	1280	2.5021	1.0293
2.507	3.52	1285	2.5013	1.0196
2.5713	3.53	1290	2.4978	1.0664
2.4783	3.55	1295	2.4958	1.0530
2.5874	3.56	1300	2.4968	1.0059
2.5744	3.57	1305	2.5078	1.0287
2.5701	3.59	1310	2.4971	1.0366
2.5366	3.6	1315	2.4897	1.0191
2.5679	3.62	1320	2.4830	1.0223
2.5239	3.63	1325	2.4833	1.0784
2.5411	3.64	1330	2.4851	1.1522
2.5037	3.66	1335	2.4792	1.0928
2.5907	3.67	1340	2.4750	1.0187
2.5107	3.68	1345	2.4805	1.0873
2.5908	3.7	1350	2.4753	1.0098
2.6274	3.71	1355	2.4765	1.0045
2.5708	3.73	1360	2.4597	1.0456
2.6039	3.74	1365	2.4503	1.0485
2.5305	3.75	1370	2.4439	1.0126
2.4878	3.77	1375	2.4407	1.0162
2.5055	3.78	1380	2.4421	1.0605
2.5249	3.79	1385	2.4499	1.1163
2.5508	3.81	1390	2.4654	1.1472
2.5827	3.82	1395	2.4510	1.0561
2.6148	3.83	1400	2.4496	0.9998
2.5763	3.85	1405	2.4417	1.0067
2.6077	3.86	1410	2.4458	1.0682
2.5388	3.88	1415	2.4352	1.0820
2.5235	3.89	1420	2.4277	1.0784
2.4996	3.9	1425	2.4245	1.0671
2.5601	3.92	1430	2.4202	1.0650
2.5805	3.93	1435	2.4199	1.0530
2.5841	3.94	1440	2.4228	1.0797
2.4877	3.96	1445	2.4284	1.1159
2.5542	3.97	1450	2.4190	1.0575
2.5961	3.98	1455	2.4162	1.0676
2.495	4.0	1460	2.4165	1.0821
2.6157	4.01	1465	2.4119	1.0117
2.5415	4.03	1470	2.4089	1.0110
2.4916	4.04	1475	2.4032	1.0498
2.5445	4.05	1480	2.3997	1.0429
2.4941	4.07	1485	2.4008	1.0141
2.5113	4.08	1490	2.3975	1.0357
2.4707	4.1	1495	2.3938	1.0288
2.4952	4.11	1500	2.3910	1.0300
2.5017	4.12	1505	2.3861	1.0813
2.5566	4.14	1510	2.3919	1.1082
2.5754	4.15	1515	2.3947	1.0074
2.6138	4.16	1520	2.4040	0.9989
2.5024	4.18	1525	2.3949	1.0039
2.5136	4.19	1530	2.3993	1.0496
2.5646	4.21	1535	2.3981	1.0729
2.4556	4.22	1540	2.3952	1.0494
2.5774	4.23	1545	2.3924	1.0345
2.5126	4.25	1550	2.3888	1.0306
2.4596	4.26	1555	2.3960	1.0775
2.521	4.27	1560	2.3978	1.1025
2.6304	4.29	1565	2.3885	1.0433
2.543	4.3	1570	2.3849	1.0072
2.5601	4.31	1575	2.3855	1.0110
2.6304	4.33	1580	2.3878	1.0369
2.4121	4.34	1585	2.3783	1.0366
2.4261	4.36	1590	2.3746	1.0307
2.5038	4.37	1595	2.3789	1.0611
2.5391	4.38	1600	2.3849	1.0738
2.4341	4.4	1605	2.3779	1.0573
2.5306	4.41	1610	2.3751	1.0460
2.5818	4.42	1615	2.3743	1.0251
2.5531	4.44	1620	2.3723	1.0209
2.51	4.45	1625	2.3755	1.0316
2.5788	4.47	1630	2.3725	1.0396
2.5701	4.48	1635	2.3663	1.0292
2.4194	4.49	1640	2.3641	1.0261
2.5439	4.51	1645	2.3629	1.0376
2.4527	4.52	1650	2.3629	1.0563
2.5705	4.53	1655	2.3654	1.0766
2.4552	4.55	1660	2.3708	1.0802
2.5657	4.56	1665	2.3638	1.0248
2.5371	4.57	1670	2.3639	1.0053
2.5365	4.59	1675	2.3626	1.0072
2.5383	4.6	1680	2.3584	1.0170
2.546	4.62	1685	2.3574	1.0469
2.6006	4.63	1690	2.3517	1.0509
2.4894	4.64	1695	2.3489	1.0452
2.4732	4.66	1700	2.3489	1.0586
2.4933	4.67	1705	2.3501	1.0694
2.4784	4.68	1710	2.3472	1.0647
2.5349	4.7	1715	2.3419	1.0299
2.553	4.71	1720	2.3420	1.0115
2.5035	4.73	1725	2.3415	1.0117
2.561	4.74	1730	2.3418	1.0242
2.4773	4.75	1735	2.3420	1.0325
2.4691	4.77	1740	2.3422	1.0394
2.4959	4.78	1745	2.3405	1.0418
2.4928	4.79	1750	2.3394	1.0449
2.5058	4.81	1755	2.3392	1.0489
2.5193	4.82	1760	2.3390	1.0506
2.5369	4.83	1765	2.3392	1.0384
2.4843	4.85	1770	2.3398	1.0236
2.5074	4.86	1775	2.3400	1.0150
2.4941	4.88	1780	2.3386	1.0150
2.4352	4.89	1785	2.3370	1.0172
2.4372	4.9	1790	2.3362	1.0208
2.4855	4.92	1795	2.3358	1.0238
2.4516	4.93	1800	2.3355	1.0276
2.5281	4.94	1805	2.3356	1.0312
2.5519	4.96	1810	2.3352	1.0318
2.4641	4.97	1815	2.3349	1.0294
2.4515	4.98	1820	2.3348	1.0284
2.553	5.0	1825	2.3347	1.0286

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.2.dev0
• Tokenizers 0.11.0