NVIDIA
NVIDIA
STT En Conformer-Transducer Large
Model
NVIDIA
NVIDIA
STT En Conformer-Transducer Large

Conformer-Transducer-Large model for English Automatic Speech Recognition, Trained on NeMo ASRSET

3 Versions
1.10.0Selected
06/23/2022 7:53 PM UTC460.16 MB
Accuracy
KeyValue
LibriSpeech Dev-clean1.6
LibriSpeech Test-other3.7
LibriSpeech Dev-other3.5
LibriSpeech Test-clean1.7
Model
KeyValue
Encoder Dimension512
Number of Layers17
ArchitectureConformer-Transducer-Large
DatasetNeMo ASRSET 3.0
OutputsText in English
InputsSpeech in English
Number of Weights120M
02/15/2022 10:42 PM UTC426.45 MB
Accuracy
KeyValue
LibriSpeech Dev-clean1.5
LibriSpeech Test-other3.6
LibriSpeech Dev-other3.5
LibriSpeech Test-clean1.7
Model
KeyValue
Encoder Dimension512
Number of Layers17
ArchitectureConformer-Transducer-Large
DatasetNeMo ASRSET 2.0
OutputsText in English
InputsSpeech in English
Number of Weights120M
09/21/2021 10:19 PM UTC427.57 MB
Accuracy
KeyValue
LibriSpeech Dev-clean2.4
LibriSpeech Dev-other5.5
LibriSpeech Test-clean2.6
LibriSpeech Test-other5.8
Model
KeyValue
ArchitectureConformer-Transducer-Large
DatasetNeMo ASRSET 1.4.1
Encoder Dimension512
InputsSpeech in English
Number of Layers17
Number of Weights120M
OutputsText in English

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.