You can deploy this model and start earning money today!

alinerodrigues/
wav2vec2-xlsr-1b-mecita-portuguese-all-clean-06

Name: wav2vec2-xlsr-1b-mecita-portuguese-all-clean-06
Availability: InStock

Views

No views yet

wav2vec2-xlsr-1b-mecita-portuguese-all-clean-06

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
24.9822	1.0	67	3.8001	0.9668	0.8169
6.3192	2.0	134	3.2618	0.9794	0.9773
4.1532	3.0	201	3.2294	0.9770	0.9800
4.1532	4.0	268	2.8781	0.9946	0.9900
3.3713	5.0	335	0.2855	0.1882	0.0521
0.6517	6.0	402	0.1736	0.1131	0.0330
0.6517	7.0	469	0.1476	0.1032	0.0300
0.318	8.0	536	0.1320	0.0880	0.0254
0.2177	9.0	603	0.1313	0.0856	0.0252
0.2177	10.0	670	0.1375	0.0897	0.0268
0.2075	11.0	737	0.1494	0.0873	0.0265
0.191	12.0	804	0.1243	0.0823	0.0243
0.191	13.0	871	0.1267	0.0816	0.0245
0.1701	14.0	938	0.1371	0.0812	0.0246
0.17	15.0	1005	0.1413	0.0799	0.0253
0.17	16.0	1072	0.1368	0.0812	0.0247
0.1462	17.0	1139	0.1353	0.0850	0.0257
0.1571	18.0	1206	0.1413	0.0880	0.0259
0.1571	19.0	1273	0.1362	0.0785	0.0242
0.1275	20.0	1340	0.1293	0.0765	0.0230
0.1233	21.0	1407	0.1318	0.0782	0.0243
0.1233	22.0	1474	0.1392	0.0853	0.0250
0.1269	23.0	1541	0.1344	0.0853	0.0254
0.133	24.0	1608	0.1366	0.0812	0.0249
0.133	25.0	1675	0.1249	0.0779	0.0238
0.1182	26.0	1742	0.1394	0.0840	0.0254
0.1221	27.0	1809	0.1415	0.0843	0.0259
0.1221	28.0	1876	0.1437	0.0812	0.0253
0.1061	29.0	1943	0.1461	0.0840	0.0260
0.1115	30.0	2010	0.1399	0.0829	0.0249
0.1115	31.0	2077	0.1456	0.0758	0.0239
0.091	32.0	2144	0.1426	0.0785	0.0241