NVIDIA
NVIDIA
STT Ca Quartznet15x5
Model
NVIDIA
NVIDIA
STT Ca Quartznet15x5

Speech To Text (STT) model based on QuartzNet for recognizing Catalan speech.

  • 1 Version
    1.0.0rc1Selected
    03/10/2021 2:32 AM UTC67.97 MB
    Accuracy
    KeyValue
    MCV dev set WER (%)6.0
    Model
    KeyValue
    ArchitectureQuartzNet
    INPUTSINPUTS 16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)
    OUTPUTSTRANSCRIPTION TEXT