Bryan Frederick Marks
Bryan Frederick Marks
+1 to this issue. Cannot eas build android. `Expo doctor` says: `🎉 Didn't find any issues with the project!` Gradle Logs say: `> Project with path ':expo-modules-core' could not be...
Hey Morten, The training logs say: ``` grep: /tf_files/log-resized-images.txt: Transport endpoint is not connected grep: /tf_files/log-resized-images.txt: Transport endpoint is not connected Resizing 2632855.jpg for label test2 into /tf_files/images/resized/test2 mkdir: cannot...
I have a Macbook Pro. I've read some articles about using GPU processors to speed up the training. I'm going to do a deep dive in the next few weeks....
Should train the model on the cloud using a EC2 GPU instance or SageMaker.
same issue - this is more time consuming than building from scratch
Would also like to test
We also notice OpenAILLMService#0 processing time of 1.7s on pipecat 0.95. Gemini 2.5-flash is slightly faster but just 0.1 second or so and the reasoning seems lower