Error System.AccessViolationException on inference from .NET

[Henderz]

Error on Inference (not training)

• Have I written custom code (as opposed to running examples on an unmodified clone of the repository):Yes
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04):Windows 10
• TensorFlow installed from (our builds, or upstream TensorFlow):NA
• TensorFlow version (use command below):NA
• Python version: NA
• Bazel version (if compiling from source):NA
• GCC/Compiler version (if compiling from source):NA
• CUDA/cuDNN version:NA
• GPU model and memory:NA
• Exact command to reproduce: objDeepSpeech.IntermediateDecodeWithMetadata(objStream, 1);

Bug?

I am using DeepSpeech for inference from microphone stream captured via CSCore audio module. I have custom code for VAD and get Intermediate decoding done to get sentence wise live transcription.

Models: 9.0.3 Pre-Trained English Audio Model and custom Scorers with the same hyper-parameters as the Pre-Trained Scorer.

This works but at random times I get

StackOverflowException
from objDeepSpeech.FeedAudioContent(objStream, buffers, Convert.ToUInt32(buffers.Length));
or
System.AccessViolationException: 'Attempted to read or write protected memory. This is often an indication that other memory is corrupt.'
from objDeepSpeech.IntermediateDecodeWithMetadata(objStream, 1);

The errors originate from within libdeepspeech.so so I am not able to debug any further. Any help is much appreciated. Thanks.

[ftyers]

See #3693