You can deploy this model and start earning money today!

alinerodrigues/
wav2vec2-xlsr-1b-mecita-portuguese-all-03

Name: wav2vec2-xlsr-1b-mecita-portuguese-all-03
Availability: InStock

Views

No views yet

wav2vec2-xlsr-1b-mecita-portuguese-all-03

This model is a fine-tuned version of jonatasgrosman/wav2vec2-xls-r-1b-portuguese 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:

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
28.3357	1.0	86	3.1566	0.9563	0.8944
7.8101	2.0	172	3.0125	1.0	1.0
3.7309	3.0	258	2.8713	0.9850	0.9913
4.3991	4.0	344	2.8582	0.9629	0.9566
4.1408	5.0	430	2.8240	0.9717	0.9362
3.734	6.0	516	2.7698	0.9520	0.8393
3.3985	7.0	602	2.7666	0.9741	0.7636
3.3985	8.0	688	0.6822	0.5838	0.1672
1.9243	9.0	774	0.2183	0.1343	0.0397
0.5075	10.0	860	0.1937	0.1074	0.0348
0.3325	11.0	946	0.1613	0.0953	0.0305
0.2617	12.0	1032	0.1571	0.0884	0.0283
0.2373	13.0	1118	0.1504	0.0851	0.0273
0.2062	14.0	1204	0.1571	0.0844	0.0267
0.2062	15.0	1290	0.1472	0.0813	0.0260
0.1863	16.0	1376	0.1408	0.0770	0.0247
0.1731	17.0	1462	0.1498	0.0796	0.0254
0.1431	18.0	1548	0.1543	0.0827	0.0257
0.1476	19.0	1634	0.1495	0.0834	0.0264
0.1432	20.0	1720	0.1473	0.0815	0.0252
0.1263	21.0	1806	0.1573	0.0782	0.0249
0.1263	22.0	1892	0.1528	0.0765	0.0256
0.1255	23.0	1978	0.1602	0.0792	0.0261
0.1151	24.0	2064	0.1614	0.0820	0.0263
0.1331	25.0	2150	0.1467	0.0792	0.0242
0.1083	26.0	2236	0.1459	0.0801	0.0248
0.1072	27.0	2322	0.1616	0.0773	0.0247
0.1002	28.0	2408	0.1543	0.0751	0.0244
0.1002	29.0	2494	0.1590	0.0801	0.0249
0.0995	30.0	2580	0.1642	0.0773	0.0249
0.1024	31.0	2666	0.1483	0.0792	0.0245
0.0966	32.0	2752	0.1509	0.0749	0.0239
0.0947	33.0	2838	0.1546	0.0803	0.0247
0.0918	34.0	2924	0.1578	0.0770	0.0241
0.0855	35.0	3010	0.1555	0.0787	0.0249
0.0855	36.0	3096	0.1552	0.0782	0.0245