Merge pull request #224361 from ArcherAZ/patch-51

Update how-to-custom-speech-test-and-train.md

Author: prmerger-automator[bot]

articles/cognitive-services/Speech-Service/how-to-custom-speech-test-and-train.md

@@ -35,7 +35,7 @@ The following table lists accepted data types, when each data type should be use
 | [Audio only](#audio-data-for-training-or-testing) | Yes (visual inspection) | 5+ audio files | Yes (Preview for `en-US`) | 1-20 hours of audio |
 | [Audio + human-labeled transcripts](#audio--human-labeled-transcript-data-for-training-or-testing) | Yes (evaluation of accuracy) | 0.5-5 hours of audio | Yes | 1-20 hours of audio |
 | [Plain text](#plain-text-data-for-training) | No | Not applicable | Yes | 1-200 MB of related text |
-| [Structured text](#structured-text-data-for-training) (public preview) | No | Not applicable | Yes | Up to 10 classes with up to 4,000 items and up to 50,000 training sentences |
+| [Structured text](#structured-text-data-for-training) | No | Not applicable | Yes | Up to 10 classes with up to 4,000 items and up to 50,000 training sentences |
 | [Pronunciation](#pronunciation-data-for-training) | No | Not applicable | Yes | 1 KB to 1 MB of pronunciation text |
 
 Training with plain text or structured text usually finishes within a few minutes.