Hi,
I'm working on a system that cannot give more than 2GB memory for java to run. However, I need to be able to decode longer utterances (60+ seconds) containing several sentences. I saw that the new API can produce multiple results for one utterance, but when I tried this on a an utterance of only 25 seconds my memory limits were exceeded.
Do you have any suggestions as to how I should proceed? It is not feasible for me to manually segment these utterances into smaller audio files.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
For analysis of this problem you need to provide the data to reproduce your problem - audio file, exact setup you are using, java version, JVM, OS information.
Java is resource-consuming overall but optimized setup is possible. Please share the information to get help.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
I'm working on a system that cannot give more than 2GB memory for java to run. However, I need to be able to decode longer utterances (60+ seconds) containing several sentences. I saw that the new API can produce multiple results for one utterance, but when I tried this on a an utterance of only 25 seconds my memory limits were exceeded.
Do you have any suggestions as to how I should proceed? It is not feasible for me to manually segment these utterances into smaller audio files.
Dear Jeff
For analysis of this problem you need to provide the data to reproduce your problem - audio file, exact setup you are using, java version, JVM, OS information.
Java is resource-consuming overall but optimized setup is possible. Please share the information to get help.