NVIDIA
STT Pl FastConformer Hybrid Transducer-CTC Large P&C
Model
NVIDIA
STT Pl FastConformer Hybrid Transducer-CTC Large P&C

This collection contains the large version (114M) of the Polish speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.

2 Versions
1.21.0Selected
07/20/2023 11:33 PM UTC437.96 MB
Accuracy
KeyValue
MCV12.0 TEST8.3 %
MLS DEV6.8 %
MCV12.0 DEV5.3 %
VOXPOPULI DEV10.9 %
VOXPOPULI TEST8.1 %
MLS TEST5.1 %
Accuracy-PC
KeyValue
MCV12.0 TEST10.6 %
MLS DEV15.0 %
MCV12.0 DEV7.9 %
VOXPOPULI DEV13.6 %
VOXPOPULI TEST11.0 %
MLS TEST9.8 %
Model
KeyValue
ARCHITECTUREFastConformer Hybrid Transducer-CTC Large
INPUTS16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)
OUTPUTSTRANSCRIBED SPEECH
05/02/2023 6:51 PM UTC437.98 MB
Accuracy
KeyValue
MCV12.0 TEST8.7 %
MLS DEV7.1 %
MCV12.0 DEV6.0 %
VOXPOPULI DEV11.3 %
VOXPOPULI TEST8.5 %
MLS TEST5.8 %
Accuracy-PC
KeyValue
MCV12.0 TEST11.0 %
MLS DEV16.0 %
MCV12.0 DEV8.9 %
VOXPOPULI DEV14.0 %
VOXPOPULI TEST11.4 %
MLS TEST11.0 %
Model
KeyValue
ARCHITECTUREFastConformer Hybrid Transducer-CTC Large
INPUTS16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)
OUTPUTSTRANSCRIBED SPEECH

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.