IDOL Speech Server can normalize text in the following languages.
Australian English (ENAU ) |
Hindi (HIIN ) |
Brazilian Portuguese (PTBR ) |
Hungarian (HUHU ) |
British English (ENUK ) |
Italian (ITIT ) |
Canadian English (ENCA ) |
Irish English (ENIE ) |
Canadian French (FRCA ) |
Japanese (JAJP ) |
Castilian Spanish (ESES ) |
Korean (KOKR ) |
Chinese Mandarin (ZHCN ) |
Latin American Spanish (ESLA ) |
Danish (DADK ) |
Modern Standard Arabic (ARMSA ) |
Dutch (NLNL ) |
Russian (RURU ) |
Farsi (FAIR ) |
Singaporean English (ENSG ) |
French (FRFR ) |
South African English (ENZA ) |
Generic English (ENXX ) |
Turkish (TRTR ) |
German (DEDE ) |
U.S English (ENUS ) |
Gulf Arabic (ARGU ) |
U.S Spanish (ESUS ) |
For Japanese, Korean, Mandarin, and Taiwanese Mandarin languages, you must use the SegmentText
task to segment the text before you submit it for normalization (see Segment Text).
For transcripts in languages for which normalization is not supported, you must manually normalize the text (see Manually Normalize Text).
|