Closed Green-Sky closed 2 months ago
trace of the assert:
#0 0x00007ffff79c3ddc in __pthread_kill_implementation () from /nix/store/1zy01hjzwvvia6h9dq5xar88v77fgh9x-glibc-2.38-44/lib/libc.so.6
#1 0x00007ffff79749c6 in raise () from /nix/store/1zy01hjzwvvia6h9dq5xar88v77fgh9x-glibc-2.38-44/lib/libc.so.6
#2 0x00007ffff795d8fa in abort () from /nix/store/1zy01hjzwvvia6h9dq5xar88v77fgh9x-glibc-2.38-44/lib/libc.so.6
#3 0x00007ffff7ebb3e3 in ggml_compute_forward_conv_1d_stage_0 () from /home/green/workspace/bark.cpp/build/encodec.cpp/ggml/src/libggml.so
#4 0x00007ffff7ed7224 in ggml_graph_compute_thread () from /home/green/workspace/bark.cpp/build/encodec.cpp/ggml/src/libggml.so
#5 0x00007ffff79c20e4 in start_thread () from /nix/store/1zy01hjzwvvia6h9dq5xar88v77fgh9x-glibc-2.38-44/lib/libc.so.6
also I noticed that threads are constantly recreated, not sure if its ggml or the usage of it, but thats going to be slow on windows.
I used the f16 version of the encodec
model and it works :tada:
Using the f16 version of bark
works as well :partying_face:
Cool! Thanks for testing this :) I'll try to investigate the issue with the F32 weights.
The readme states:
but the script also requires you to specify
--vocab-path VOCAB_PATH
, in which thevocab.txt
can be found. Saidvocab.txt
got deleted, I found this pr and downloaded it from there.Conversion seems to go well, but while it downloaded the
encodec
model too, it does not seems to convert that. Also, why is the resultingggml_weights.bin
only 4gig, when the source model is 12gig and presumably 32bit floats. (I ran it without--use-f16
) There also seem to be no instructions on how to convert theencodec
model forencodec.cpp
(but there is aconvert.py
which I then used).I ran bark
main
and it seems to work except forencodec
::sweat_smile: