Statements (32)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
automatic speech recognition system
|
| gptkbp:availableOn |
gptkb:GitHub
|
| gptkbp:canBeTrainedOn |
custom datasets
|
| gptkbp:developedBy |
gptkb:NVIDIA
|
| gptkbp:documentation |
https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/stable/asr/models.html
|
| gptkbp:firstReleased |
2019
|
| gptkbp:hasFeature |
real-time transcription
punctuation restoration speaker diarization inverse text normalization |
| gptkbp:hasModel |
gptkb:Jasper
gptkb:CitriNet gptkb:Conformer gptkb:ContextNet gptkb:QuartzNet |
| https://www.w3.org/2000/01/rdf-schema#label |
NeMo ASR
|
| gptkbp:integratesWith |
gptkb:NVIDIA_Triton_Inference_Server
gptkb:NVIDIA_Riva gptkb:PyTorch |
| gptkbp:license |
Apache 2.0
|
| gptkbp:openSource |
true
|
| gptkbp:partOf |
gptkb:NVIDIA_NeMo
|
| gptkbp:platform |
gptkb:microprocessor
gptkb:graphics_card |
| gptkbp:supportsLanguage |
gptkb:German
gptkb:Mandarin_Chinese gptkb:Russian gptkb:Spanish English |
| gptkbp:usedFor |
speech-to-text
|
| gptkbp:bfsParent |
gptkb:Nvidia_NeMo
|
| gptkbp:bfsLayer |
6
|