Resources for languages other than english

• French:
  • ​Sphinx 3.3 & LIUM Speech Tools
    • Acoustic Models
    • trigram and quadrigram Language Models
  • ​cookerspot - speech recognition work being done with Julius (tutorial for install of Julius)

• French
  • ​Eurom1-FR
  • with licencing restrictions
    • ​ShtookaFree Audio base of French Words - CC with attribution

• Spanish:
  • ​Spanish HUB4
    • Acoustic Models
    • trigram Language Models
  • ​Hispavoces Spanish voices for Festival (no source audio listed, but may be to contact them to get it ...)

• Dutch
  • ​IFA Spoken Language corpus
  • ​Spoken Dutch Corpus (CGN = Corpus gesproken Nederlands) project (may be used for scientific research and the development of non-commercial products)

• Languages for Festival (a good starting place to set up a new language for Speech Recognition)
  • ​FestLang

• ​Non-native Speech Databases (wikipedia article)

• Danish
  • ​DanPASS - Danish Phonetically Annotated Spontaneous Speech (licensing?)

• ​Haitian Creole data

• ​Thai

• ​Bengali