You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for this helpful project :), I encountered some issues while using it: I used SileroVad for real-time voice activity detection and noticed that the native memory usage kept increasing. I found that some resources might not be released properly:
After using getInputTensors to obtain OnnxTensor, the close method was not called to release the resources.
The result of session.run was not closed after usage.
When using getModel to access the assets stream, the stream was not explicitly closed. It might be better to cache the byte data instead of loading the model repeatedly.
The text was updated successfully, but these errors were encountered:
Thank you for this helpful project :), I encountered some issues while using it: I used SileroVad for real-time voice activity detection and noticed that the native memory usage kept increasing. I found that some resources might not be released properly:
The text was updated successfully, but these errors were encountered: