-
Notifications
You must be signed in to change notification settings - Fork 277
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Bug: Python stt client failing on AARCH with segmentation fault #2284
Comments
@wasertech Not sure if it's important but the TensorFlow team recommends using these docker images, and that's why I picked this docker image to try to run |
@lissyx / @wasertech FYI, I changed the base image from |
After doing a little bit more debugging with
It seems that its fails when calling a TensorFlow function |
Full stack trace, it seems that the last successful to
|
What's this? Never seen this message. Could it be relevant? Also, you seem to be using non-english models (nothing wrong with it just makes replication more cumbersome).
|
Seems to be related to docker. Added the suggested flags to get rid of the warning, and not much changed.
yes
https://coqui.gateway.scarf.sh/spanish/jaco-assistant/v0.0.1/model.tflite
Same results :( |
@wasertech / @lissyx Unfortunately, the information I provided about the English model causing a The problem seems to be with the Spanish model. The information I provided regarding the I am closing this ticket since this problem seems to be related more to the Spanish model and not coqui Thanks again for all your help and pointers :) |
I might add the model works perfectly on bear metal inside a venv on x86-64. |
Describe the bug
I am trying to use the recently published artifact
stt-1.4.0a6-cp39-cp39-linux_aarch64.whl
. However, I am getting aSegmentation Fault
error when trying to use thestt
python
client.I have a sample project that can be run against any
aarch
workstation in order to easily replicate the error. The same error happens when running against a mac with an M1 chip, but I am sure if the same artifact could be used (in theory, it should be the same?).To Reproduce
Here are the steps to reproduce the error (assuming you have an
aarch
workstation):git clone [email protected]:mariano-balto/coqui-aarch-segmentation-fault.git
cd coqui-aarch-segmentation-fault
docker build . -t coqui-aarch-segmentation-fault
docker run coqui-aarch-segmentation-fault
Expected behavior
The
stt
client should return an inference, however, its erroring out with the following output:Environment (please complete the following information):
Additional context
The text was updated successfully, but these errors were encountered: