add a recommended limit on the number of speaker ids

Author: Daniel Nurkowski

docs/speech-to-text/features/speaker-identification.mdx

@@ -31,13 +31,13 @@ By tagging known speakers with consistent labels, speaker identification makes t
 
 To use speaker identification you must enable diarization in the [speaker mode](../features/diarization.mdx#diarization-modes) and then follow the two steps below:
 
-- **Enrollment** — For each speaker you want to recognize, generate identifiers from short audio clips (5–30s) where they ideally speak alone.
+- **Enrollment** - For each speaker you want to recognize, generate identifiers from short audio clips (5–30s) where they ideally speak alone.
   To improve robustness, you can enroll the same speaker with multiple clips recorded under different acoustic conditions, selected to represent the degree of variety and quality that could be expected in the target audio.
 
-- **Identification** — Use the enrolled identifiers in transcription jobs to label known speakers with meaningful names (for example, `Alice` or `John`).  The system matches voices to identifiers and tags the output with the desired labels.
+- **Identification** - Use the enrolled identifiers in transcription jobs to label known speakers with meaningful names (for example, `Alice` or `John`). The system matches voices to identifiers and tags the output with the desired labels.
 
 :::info
-Labels for identified speakers must not use reserved internal labels (UU, S1, S2, etc.) and must not include leading or trailing spaces.
+It is recommended to keep the number of speaker ID's to a minimum for best accuracy. The number of speaker ID's should not go above 50. Furthermore, labels for identified speakers must not use reserved internal labels (UU, S1, S2, etc.) and must not include leading or trailing spaces.
 :::
 
 ## Known caveats