silero-vad
silero-vad copied to clipboard
snakers4
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
First, congratulations for your work and for sharing it with the community !! https://github.com/snakers4/silero-vad/releases/tag/v3.1 indicates > Only 16kHz available now (ONNX has some issues with if-statements and / or tracing...
Just a handy issue to be notified of latest changes and micro-releases (we will mostly changing the models)
Thinking about new features, medium term: [](https://api.gh-polls.com/poll/01FRHQ0TATC7CTV8ES2SKA1RKW/Higher%20accuracy/vote) [](https://api.gh-polls.com/poll/01FRHQ0TATC7CTV8ES2SKA1RKW/Python%20packages/vote) [](https://api.gh-polls.com/poll/01FRHQ0TATC7CTV8ES2SKA1RKW/8k%20support%20for%20ONNX/vote) [](https://api.gh-polls.com/poll/01FRHQ0TATC7CTV8ES2SKA1RKW/Higher%20performance/vote) [](https://api.gh-polls.com/poll/01FRHQ0TATC7CTV8ES2SKA1RKW/Wake%20word%20detection%20models/vote) [)](https://api.gh-polls.com/poll/01FRHQ0TATC7CTV8ES2SKA1RKW/Other%20model%20formats%20(please%20comment)/vote) [)](https://api.gh-polls.com/poll/01FRHQ0TATC7CTV8ES2SKA1RKW/Music%20detection%20for%20longer%20utterances%20(several%20seconds)/vote) [)](https://api.gh-polls.com/poll/01FRHQ0TATC7CTV8ES2SKA1RKW/Audio%20event%20classification%20for%20longer%20utterances%20(several%20seconds)/vote)
While the VAD (especially the micro one) was explicitly designed for IOT / edge / mobile use cases, we do not have the resource or expertise to provide instructions for...
Hi, I found the vad model is not very good at filtering background vocals , for example TV vocals. Are there parameters to adjust to filtering background vocals ？ Thanks.
## ❓ Questions and Help I found the speech timestamps respectively obtained from pytorch and silero-vad-onnx.cpp is somewhat different. The input file is 'en_example.wav' which downloaded from torch.hub. the speech...
Hi, Just wondering is there no onnx gpu support? Would it not be any faster than jit when moving the model to CUDA with a .to() ? This is what...
Please tell me if I can fine-tune this model on urdu dataset or train from scratch with same architecture for Urdu?? In short please elaborate the architecture of this model...
## 🐛 Bug On some audio, the quality of the VAD is reallly worse in the latest version v4.0, compared to what it was in v3.1 More precisely, v4.0 detects...
## 🚀 Feature ## Motivation ## Pitch ## Alternatives ## Additional context