Issues
- 0
docker build error
#40 opened by ben-8878 - 2
- 1
Improve confidence scoring algorithm
#33 opened by greed2411 - 0
Ontology/context (on the fly LM computation and graph composition or lattice rescoring)
#31 opened by greed2411 - 0
In memory audio codec conversion
#32 opened by greed2411 - 0
Integration with MACE for better performance (memory optim, quantization, etc.)
#35 opened by greed2411 - 0
- 1
Transformer LM lattice rescoring
#34 opened by greed2411 - 1
Speech end-pointing
#37 opened by greed2411 - 1
- 0
- 1
Instructions
#29 opened by dpny518 - 3
Add support for OGG_OPUS
#26 opened by seyuf - 2
- 1
typo: not ./lib but ../lib in rpath
#19 opened by al-zatv - 1
- 2
Bidi streaming proposal end of utterance detection
#13 opened by seyuf - 1
models without ivectors?
#18 opened by al-zatv - 2
Android and iOS samples
#17 opened by dpny518 - 2
Components versions to build stable
#14 opened by kvishnivetsky - 1
sample_rate_hertz has no effect
#12 opened by cogmeta - 2
Word StartTime & EndTime should be changed by reference kaldi nnet3 code.
#10 opened by kimkwangho82 - 2
make word confidence and timings optional
#5 opened by lepisma - 7
Dockerfile doesn't work
#7 opened by lepisma - 3
Add a sample testing model
#1 opened by lepisma - 0
- 1
Server hangs up on bad audio format
#2 opened by deep110 - 0