You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am using an aarch64 android mobile device using android 12 with 2GB RAM, 16GB ROM
when i use the android app example with the whisper_tiny_cpu_int8_model.onnx as provided, it works without issues. the model size if around 74MB.
When i replace this model with whisper_base_cpu_int8_model.onnx, which has a size of 140MB, it fails with out of memory error as it tries to access java heap memory instead of native memory.
All i did was change the model, i did not change the code anywhere. while running the app, i still have 500MB of free RAM available and still i get out of memory error.
the error log is below:
02-13 20:54:39.039 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:39.039 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:39.063 1973 2038 I le.whisperLoca: Alloc young concurrent copying GC freed 2084(104KB) AllocSpace objects, 2(1488KB) LOS objects, 3% free, 138MB/143MB, paused 137us,47us total 23.358ms
02-13 20:54:39.063 1973 2038 I le.whisperLoca: Forcing collection of SoftReferences for 133MB allocation
02-13 20:54:39.064 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:39.140 1973 2038 I le.whisperLoca: Alloc concurrent copying GC freed 399(27KB) AllocSpace objects, 2(134MB) LOS objects, 49% free, 3879KB/7758KB, paused 128us,39us total 75.682ms
02-13 20:54:41.492 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:41.492 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:41.507 1973 2038 I le.whisperLoca: Alloc young concurrent copying GC freed 49(47KB) AllocSpace objects, 0(0B) LOS objects, 4% free, 137MB/143MB, paused 148us,35us total 15.306ms
02-13 20:54:41.508 1973 2038 I le.whisperLoca: Forcing collection of SoftReferences for 133MB allocation
02-13 20:54:41.508 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:41.534 1973 2038 I le.whisperLoca: Alloc concurrent copying GC freed 738(47KB) AllocSpace objects, 0(0B) LOS objects, 4% free, 137MB/143MB, paused 298us,37us total 26.083ms
02-13 20:54:41.535 1973 2038 W le.whisperLoca: Throwing OutOfMemoryError "Failed to allocate a 140086368 byte allocation with 6291456 free bytes and 118MB until OOM, target footprint 150295640, growth limit 268435456" (VmSize 14958388 kB)
02-13 20:54:41.535 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:41.535 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:41.549 1973 2038 I le.whisperLoca: Alloc young concurrent copying GC freed 4(31KB) AllocSpace objects, 0(0B) LOS objects, 4% free, 137MB/143MB, paused 128us,40us total 13.928ms
02-13 20:54:41.550 1973 2038 I le.whisperLoca: Forcing collection of SoftReferences for 133MB allocation
02-13 20:54:41.550 1973 2038 I le.whisperLoca: Starting a blocking GC Alloc
02-13 20:54:41.575 1973 2038 I le.whisperLoca: Alloc concurrent copying GC freed 34(16KB) AllocSpace objects, 0(0B) LOS objects, 4% free, 137MB/143MB, paused 128us,40us total 25.049ms
02-13 20:54:41.576 1973 2038 W le.whisperLoca: Throwing OutOfMemoryError "Failed to allocate a 140086368 byte allocation with 6291456 free bytes and 118MB until OOM, target footprint 150294824, growth limit 268435456" (VmSize 14958388 kB)
how can I execute this? i should not be getting any memory error here. i generated the model using --no_audio_decoder option.
I am using an aarch64 android mobile device using android 12 with 2GB RAM, 16GB ROM
when i use the android app example with the whisper_tiny_cpu_int8_model.onnx as provided, it works without issues. the model size if around 74MB.
When i replace this model with whisper_base_cpu_int8_model.onnx, which has a size of 140MB, it fails with out of memory error as it tries to access java heap memory instead of native memory.
All i did was change the model, i did not change the code anywhere. while running the app, i still have 500MB of free RAM available and still i get out of memory error.
the error log is below:
how can I execute this? i should not be getting any memory error here. i generated the model using --no_audio_decoder option.
model is here: https://drive.google.com/file/d/1mrtEbq4PGcfppTVfGK2wMqRfniBivtB5/view?usp=sharing
The text was updated successfully, but these errors were encountered: