-
Zhaoheng Ni authored
Summary: After https://github.com/pytorch/audio/issues/2873, the pre-trained Wav2Vec2 models with larger datasets can get better performances. The PR fixes the integration test of bundle `WAV2VEC2_ASR_LARGE_LV60K_10M` which predicts the word `CURIOUSITY` to `CURIOUSSITY` before but now to `CURIOUSITY` correctly. Pull Request resolved: https://github.com/pytorch/audio/pull/2910 Reviewed By: mthrok Differential Revision: D41881919 Pulled By: nateanl fbshipit-source-id: 236fd00b983a5205c731f3efa31033a6b8257cab
90162812
