New

• Tagalog language is now available. Supports code-switching between Filipino and English for bilingual speech.

Improvements

• New models for Standard Operating Point, providing significant accuracy gains across multiple languages.

  • Relative accuracy improvements: Belarusian (be) - 5%, Bulgarian (bg) - 7%, Catalan (ca) - 29%, Danish (da) - 22%, Finnish (fi) - 17%, Galician (gl) - 8%, Hungarian (hu) - 15%, Indonesian (id) - 14%, Korean (ko) - 8%, Latvian (lv) - 9%, Lithuanian (lt) - 11%, Marathi (mr) - 16%, Norwegian (no) - 12%, Romanian (ro) - 6%, Slovenian (sl) - 9%, Swedish (sv) - 6%, Thai (th) - 14%, Turkish (tr) - 32%, Ukrainian (uk) - 6%, Urdu (ur) - 15%, Vietnamese (vi) - 66%, Welsh (cy) - 17%

• Updated English model for Enhanced Operating Point

  • Improves transcription accuracy by reducing incorrect insertions, especially in scenarios such as silence, music, or background noise.

  • Resolves the following ticket: 20863.

• Updated Bilingual Malay English (en_ms) for Enhanced Operating Point

  • Delivers up to 7.8% relative accuracy improvement, with improved latency.