Parallel Processing for Longer Texts #192
Unanswered
shikharmay7
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi everyone,
I'm trying to synthesise parallely doing something like below to reduce total time for a TTS for longer texts.
It runs normally with threads=1 but not for any value >1. It throws errors like
unknown:0: unknown: block: [0,0,0], thread: [64,0,0] Assertion
index out of bounds: 0 <= tmp12 < 2048
failed.unknown:0: unknown: block: [0,0,0], thread: [65,0,0] Assertion
index out of bounds: 0 <= tmp12 < 2048
failed.unknown:0: unknown: block: [0,0,0], thread: [66,0,0] Assertion
index out of bounds: 0 <= tmp12 < 2048
failed.unknown:0: unknown: block: [0,0,0], thread: [67,0,0] Assertion
index out of bounds: 0 <= tmp12 < 2048
failed..
.
...
IMO, it's due to the assert in the decode_one_token method. Can someone please help me with this?
Beta Was this translation helpful? Give feedback.
All reactions