Fix integration test for WAV2VEC2_ASR_LARGE_LV60K_10M (#2910)

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

test/integration_tests/wav2vec2_pipeline_test.py

@@ -59,7 +59,7 @@ def test_pretraining_models(bundle):
         (WAV2VEC2_ASR_LARGE_10M, "en", "I|HAD|THAT|CURIOUSITY|BESIDE|ME|AT|THIS|MOMENT|"),
         (WAV2VEC2_ASR_LARGE_100H, "en", "I|HAD|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|"),
         (WAV2VEC2_ASR_LARGE_960H, "en", "I|HAD|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|"),
-        (WAV2VEC2_ASR_LARGE_LV60K_10M, "en", "I|HAD|THAT|CURIOUSSITY|BESID|ME|AT|THISS|MOMENT|"),
+        (WAV2VEC2_ASR_LARGE_LV60K_10M, "en", "I|HAD|THAT|CURIOUSITY|BESID|ME|AT|THISS|MOMENT|"),
         (WAV2VEC2_ASR_LARGE_LV60K_100H, "en", "I|HAVE|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|"),
         (WAV2VEC2_ASR_LARGE_LV60K_960H, "en", "I|HAVE|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|"),
         (HUBERT_ASR_LARGE, "en", "I|HAVE|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|"),