Skip to content

Downloads stt

The following STT models are available for download. These are compatible with TrulyNatural STT SDK 7.7.0 and later.

Contact your account representative or Sensory sales for additional languages and customizations.

Filename key

opt-vg-vad-stt-
These are pipelines made from the tpl-opt-spot-vad-lvcsr template with a US English "Voice Genie" wake word in slot 0 and an STT recognizer in slot 1.
-B
Model includes an NLU component that identifies intents and entities.
-pnc
Model includes punctuation and capitalization.
-slm
Model includes a small generative language model.

Larger models are more accurate but also require more CPU cycles.

Language Domain Size in MiB Model
English (US) automotive 226 opt-vg-vad-stt-enUS-automotive-large-1.3.14-B-pnc_63
English (US) automotive 91 opt-vg-vad-stt-enUS-automotive-medium-2.3.14-B-pnc_63
English (US) automotive 49 opt-vg-vad-stt-enUS-automotive-small-2.3.14-B-pnc_63
English (US) general 199 opt-vg-vad-stt-enUS-general-large-2.0.3-pnc_63
English (US) general 67 opt-vg-vad-stt-enUS-general-medium-2.4.3-pnc_63
English (US) general 28 opt-vg-vad-stt-enUS-general-small-2.2.3-pnc_63
English (US) general 7 opt-vg-vad-stt-enUS-general-nano-2.0.3_63
English (US) general 11 opt-vg-vad-stt-enUS-general-micro-2.0.3_63
English (British) general 196 opt-vg-vad-stt-enGB-general-large-2.0.3_63
English (British) general 64 opt-vg-vad-stt-enGB-general-medium-2.0.3_63
English (British) general 25 opt-vg-vad-stt-enGB-general-small-2.0.3_63
German general 199 opt-vg-vad-stt-deDE-general-large-2.2.3_63
German general 64 opt-vg-vad-stt-deDE-general-medium-2.3.3_63
German general 25 opt-vg-vad-stt-deDE-general-small-2.3.3_63
French general 202 opt-vg-vad-stt-frFR-general-large-2.0.3_63
French general 64 opt-vg-vad-stt-frFR-general-medium-2.3.3_63
French general 25 opt-vg-vad-stt-frFR-general-small-2.3.3_63
Italian general 197 opt-vg-vad-stt-itIT-general-large-1.2.3_63
Italian general 64 opt-vg-vad-stt-itIT-general-medium-2.3.3_63
Italian general 25 opt-vg-vad-stt-itIT-general-small-2.3.3_63
Japanese general 215 opt-vg-vad-stt-jaJP-general-large-2.2.3_63
Japanese general 64 opt-vg-vad-stt-jaJP-general-medium-2.2.3_63
Japanese general 25 opt-vg-vad-stt-jaJP-general-small-2.3.3_63
Korean general 215 opt-vg-vad-stt-koKR-general-large-2.3.3_63
Korean general 64 opt-vg-vad-stt-koKR-general-medium-2.3.3_63
Korean general 25 opt-vg-vad-stt-koKR-general-small-2.3.3_63
Spanish general 197 opt-vg-vad-stt-esES-general-large-2.2.3_63
Spanish general 64 opt-vg-vad-stt-esES-general-medium-2.4.3_63
Spanish general 25 opt-vg-vad-stt-esES-general-small-2.3.3_63

Provenance

The wake word, and the speech-to-text acoustic, language, and NLU models are owned by Sensory and have no third-party dependencies.