IntendedConsequence/vadc
Uses the excellent silero VAD with onnxruntime C api for fast detection of audio segments with speech
C++MIT
Issues
- 0
STFT in C
#12 opened by IntendedConsequence - 0
AdaptiveAudioNormalization in c
#11 opened by IntendedConsequence - 0
encoder in c
#6 opened by IntendedConsequence - 0
lstm in c
#7 opened by IntendedConsequence - 0
nn.Linear (matmul) in c
#10 opened by IntendedConsequence - 0
first layer in c
#8 opened by IntendedConsequence - 0
decoder in c
#5 opened by IntendedConsequence - 0
basic conv1d in c
#9 opened by IntendedConsequence - 0
port to tinygrad
#2 opened by IntendedConsequence - 0
support silero vad v4.0 (pytorch)
#4 opened by IntendedConsequence - 0
support 8kHz
#3 opened by IntendedConsequence - 0
port to ggml
#1 opened by IntendedConsequence