ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
STT Ru Conformer-CTC Large
Model
NVIDIA
NVIDIA
STT Ru Conformer-CTC Large

Conformer-CTC-Large model for Russian Automatic Speech Recognition, trained on Mozilla Common Voice 10.0 (Russian), Golos (Russian), Russian LibriSpeech (RuLS) and SOVA (RuAudiobooksDevices, RuDevices) datasets.

1 Version
1.13.0Selected
11/01/2022 10:26 PM UTC464.15 MB
Accuracy
KeyValue
MOZILLA COMMON VOICE 10.0 RU (DEV)3.9 %
GOLOS CROWD (TEST)2.8 %
GOLOS FARFIELD (TEST)7.1 %
RUSSIAN LIBRISPEECH (TEST)13.5 %
MOZILLA COMMON VOICE 10.0 RU (TEST)4.3 %
Model
KeyValue
ARCHITECTURECONFORMER-CTC
INPUTS16000 HZ MONO-CHANNEL AUDIO (WAV FILES)
OUTPUTSTRANSCRIBED SPEECH