mirror/whisper.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
107 Commits 1 Branch 0 Tags 17 MiB
491ecd7056
Commit Graph

28 Commits

Author SHA1 Message Date
Georgi Gerganov
8d15a1c635
ci : fix and re-enable tests (2nd try) 2022-10-21 15:57:20 +03:00
Georgi Gerganov
692aa0784f
Revert "ci : fix and re-enable tests" 
This reverts commit 80aefc9514.
 2022-10-21 15:36:19 +03:00
Georgi Gerganov
80aefc9514
ci : fix and re-enable tests 2022-10-21 15:27:30 +03:00
Georgi Gerganov
7eeef0358a
ref #52 : improve greedy sampling strategy 
Force timestamp token to be sampled if the probability sum over all
timestamp tokens is above the probability of any other token
 2022-10-18 19:48:15 +03:00
Georgi Gerganov
e30cf83158
ref #57, #62, #63 : remove unions in C-api + remove designated initializers 
We are not ready for designated initializers - many compilers do not
support this C++ feature yet, so removing it's non-trivial usages.
 2022-10-18 18:17:24 +03:00
Georgi Gerganov
d6b84b2a23
ref #62 : fix build for some compilers 
For some reason, new version of GCC panic when the struct type is not
specified explicitly
 2022-10-18 10:57:03 +03:00
Georgi Gerganov
b4a3875b2c
Revert recent sampling change 
It does not actually help and seems to produce worse results on some of
the samples
 2022-10-18 08:26:16 +03:00
Georgi Gerganov
cf67bfffa0 Fix EOT token handling 
If it is the end of the audio, pick all sampled tokens.
Otherwise, print error message.
 2022-10-18 00:53:06 +03:00
Georgi Gerganov
d14823582d Try to improve the sampling strategy a bit 
It sill fails sometimes when it does not sample a timestamp token for
the entire segment. We now print a message in such cases
 2022-10-18 00:12:51 +03:00
Georgi Gerganov
20d8e7a309 Fix memory sizes 2022-10-18 00:12:51 +03:00
Georgi Gerganov
72d967bce4 Use Accelerate framework on Apple silicon 
Huge performance improvement in the Encode (almost x2 on MacBook M1 Pro)

Also various extra optimizations:

- Multi-threaded NORM operator
- Faster GELU via F16 cast
 2022-10-18 00:12:51 +03:00
Georgi Gerganov
0ad085f5e8
ref #48 : clear results at the start of whisper_full 
This way, even if the input audio is empty, the previous results will be
removed.
 2022-10-15 09:55:28 +03:00
0/0
b799226973 check if spectogram length is <100 before doing anything else 
fixes #39
 2022-10-12 07:32:42 +03:00
Borislav Stanimirov
0b45d25151 Building with MSVC 2022-10-11 21:40:46 +03:00
Georgi Gerganov
63b6786767
Minor 2022-10-10 22:06:27 +03:00
lnyan
4bbb8a587b Add MinGW support 2022-10-09 22:26:37 +08:00
Georgi Gerganov
2ca8cc77b2 ref #17 : print whisper logs to stderr 
Only the transcribed/translted text is printed to stdout.
This way, one can redirect the result to a file.
 2022-10-08 17:28:06 +03:00
Georgi Gerganov
8c7c018893 ref #17 : add options to output result to file 
Support for:

- plain text
- VTT
- SRT
 2022-10-08 17:22:22 +03:00
Georgi Gerganov
b43b36e006 Update tests 2022-10-08 11:43:42 +03:00
Georgi Gerganov
2f069335ab Adding sanitizer tests 2022-10-08 11:43:42 +03:00
Georgi Gerganov
332c9d77fe whisper : fix bug in token sampling logic 
Could overflow buffer
 2022-10-08 09:02:41 +03:00
Georgi Gerganov
481cd685d5
ref #10 : option to keep context in "stream" example 
Seems the results become worse when we keep the context, so by default
this is not enabled
 2022-10-07 22:30:44 +03:00
Georgi Gerganov
7787b878e1
ref #16, #22 : add "offset" argument 
Allows to start processing the input audio at some offset from the
beginning. Useful for splitting a long job into multiple tasks.
 2022-10-07 22:00:40 +03:00
Georgi Gerganov
167324584b wip : rpi4 support 2022-10-05 23:03:46 +03:00
Georgi Gerganov
ce1fe95902 wip : improve makefile 2022-10-05 23:03:46 +03:00
Georgi Gerganov
6814cc9b02 Improve result printing 2022-10-04 23:18:15 +03:00
Georgi Gerganov
eba33adadd Extend C-style API with full inference methods 2022-10-04 23:18:15 +03:00
Georgi Gerganov
6b77124e01 Initial C-style interface for whisper.cpp 2022-10-04 23:18:15 +03:00