Giters

mozilla / DeepSpeech

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Illegal instruction (core dumped)

opened this issue · comments

commented

I have installed deepspeech as described and whenever i run an example i get the error above and i have tried with both, the standard pbmm and the tflite models, in case my PC don’t support AVX. And in either case i get the same error, so how is that ? Is this a bug ?

  • Have I written custom code (as opposed to running examples on an unmodified clone of the repository): No
  • OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Arch Linux
  • TensorFlow installed from (our builds, or upstream TensorFlow): Don’t have tensorflow. (Is it a requirement? ). It is not mentioned in the docs.
  • TensorFlow version (use command below): Don’t have TensorFlow
  • Python version: 3.9.5
  • Bazel version (if compiling from source): Not compiling from Source
  • GCC/Compiler version (if compiling from source): Not compiling from source.
  • CUDA/cuDNN version: No CUDA
  • GPU model and memory: Intel HD 4000, 128 of memory
  • Exact command to reproduce: Try doing the same thing on a relatively underpowered machine like Raspberry Pi 4.
commented

Second time you are purposedly not opening a support request on Discourse but on Github.

commented

in case my PC don’t support AVX

You will have to rebuild libdeepspeech.so, it is documented our binaries requires it. Performances cannot be the same without AVX.