Commit Graph

819 Commits

Author SHA1 Message Date
Marcin Mielniczuk
21e8c67a4f
Fix AVX etc. under GCC/CMake (#1174) 2023-08-19 21:39:03 +03:00
Jhen-Jie Hong
a4bb2df36a
quantize : fix load vocab crash when len is 128 (#1160)
* quantize : fix load vocab crash when len is 128

* ci : add quantize job
2023-08-06 11:04:42 +03:00
Duncan McConnell
b948361956
examples : add tinydiarization support for streaming (#1137) 2023-08-03 11:24:07 +03:00
bobqianic
a792c4079c
cmake : fix MSVC compile error C3688 (#1136)
Instead of simply using 'add_compile_options(/utf-8)' to address the MSVC compile error C3688, a better approach would be to handle it in a way that prevents passing '/utf-8' to NVCC.
2023-07-26 18:57:25 +03:00
Georgi Gerganov
7b374c9ac9
Revert "cmake : fix MSVC compile error C3688 on non-unicode Windows (#1110)"
This reverts commit fe5c1a7341.
2023-07-26 10:25:09 +03:00
Yang Shen
a32c4aa482
whisper : fix visibility warning of struct whisper_full_params by declaring in advance (#1124) 2023-07-25 19:15:57 +03:00
bobqianic
a195bf899a
cmake : enable OpenBLAS on Windows (#1128)
Fixed the issue of not being able to find OpenBLAS on the Windows platform. Even though the name of the previously released binary file was whisper-blas-bin-x64.zip, BLAS was actually not enabled. After enabling, the inference speed can increase by 3-4 times.
2023-07-25 19:15:08 +03:00
Christian
ded17dc1cf
make : fix CLBlast build on MacOS (#1120) 2023-07-25 19:12:03 +03:00
alonfaraj
a0bb409f51
make : check nvcc version and set flag (#1115) 2023-07-25 19:10:54 +03:00
xdrudis
a2684cd93a
go : implement SetSplitOnWord (#1114)
* Go binding: Implement SetSplitOnWord

* Add comment for consistency
2023-07-25 19:10:12 +03:00
Jose
1450346214
make : tests can be called as "make tests base.en" (#1113) 2023-07-25 19:09:38 +03:00
Gang Chen
fe5c1a7341
cmake : fix MSVC compile error C3688 on non-unicode Windows (#1110)
Co-authored-by: Gang Chen <cg@upiot.net>
2023-07-25 19:08:37 +03:00
Ryan Metcalfe
1fa360fc6e
readme : add OpenVINO support details (#1112) 2023-07-25 19:07:59 +03:00
Gang Chen
41bf19f613
opencl : sync opencl compilation fix in ggml (#1111) 2023-07-25 19:07:08 +03:00
Vadim Peretokin
9ad35bd740
samples : add a larger (30min) sample (#1092)
Co-authored-by: Vadim Peretokin <vadim.peretokin@carasent.com>
2023-07-25 19:00:45 +03:00
Evan Martin
fabf79fc67
whisper : expose API to let user control log output (#1060)
* expose api to let user control log output

Add
  whisper_set_log_callback()
that lets user set a callback for log messages.

Change all the
  fprintf(stderr, ...)
to call via the above.

* whisper : add <cstdarg>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-25 18:58:25 +03:00
Hrishikesh Barman
925915ae37
whisper : move progress calculation out of whisper.cpp (#1081)
Current `progress_step` was hardcoded into whisper.cpp, this resulted in
bindings having to access progress only at that step even if progress
callback was being called at every iteration.

With this change we get greater granularity progress reporting from
whisper.cpp and bindings/implementations can define their own progress step.
2023-07-25 18:53:34 +03:00
AustinMroz
97f4a7fee0
examples : add Vim plugin (#1131)
* Initial proof of concept Vim plugin

At present, this is likely only slightly better than feature parity with
the existing whisper.nvim

Known issues:
 Trailing whitespace
 Up to an existing length(5 seconds) of speech may be processed when
  listening is enabled
 CPU cycles are spent processing speech even when not listening.

Fixing these issues is likely dependent upon future efforts to create a
dedicated library instead of wrapping examples/stream

* Support $WHISPER_CPP_HOME environment variable

A minor misunderstanding of the whisper.nvim implementation resulted in
a plugin that was functional, but not a drop in replacement as it should
be now.
2023-07-25 18:34:23 +03:00
alonfaraj
3998465721
ci : more platforms coverage (#1101)
* add multi platform

* add image name

* fix

* fix /bin/sh path

* add missing \

* add all platforms for check

* remove platforms

* remove s390x

* - add arm v6
- format run cmd

* remove arm v6

* - bump checkout to v3
- use setup emsdk action
- add arch to all ubuntu jobs

* mymindstorm/setup-emsdk to v12

* add missing QEMU step

* add fail-fast: false for debug

* add freebsd

* remark all jobs except freebsd for test

* add sudo

* enable all tests again

* format

* check __AVX__ support before include immintrin.h

* try auto detect flag by cmake

* fix check for immintrin.h

* fix include check for immintrin.h

* Remove all platforms for sanitizer build except amd64

We have no clue why they failed.

---------

Co-authored-by: Alon Faraj <alon.faraj@mapcore.com>
2023-07-16 23:00:34 +03:00
Georgi Gerganov
4774d2feb0
whisper : minor OpenVINO refactoring (#1037)
Hopefully I didn't break something - haven't tested
2023-07-04 20:28:27 +03:00
Travis Cline
6f0114f4a6
go : call SetDuration appropriately (#1077) 2023-07-04 16:13:25 +03:00
Murilo Santana
66616dbd4d
go : fix context.Process call in examples (#1067) 2023-07-04 16:05:35 +03:00
Ryan Metcalfe
62b81276e0
whisper : add OpenVINO support (#1037)
* openvino: use OpenVINO encoder inference

* openvino: add python script for OpenVINO model generation

* whisper: Fix 'unused' warnings when OpenVINO isn't enabled in build

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* whisper: Fix compilation error

* whisper: revert whisper_get_openvino_path_encoder & whisper_get_openvino_path_cache to non-const func signatures

* cmake: Add openvino-encoder as separate object target

* whisper : minor style fixes

* minor : indentation fixes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-04 15:56:11 +03:00
Martin Warnaar
176d7e4e7b
readme : better wording (#1064) 2023-07-04 15:30:31 +03:00
Georgi Gerganov
70e6fcd78b
readme : add tinydiarize instructions (#1058) 2023-07-04 09:51:22 +03:00
Akash Mahajan
c8d0f5fe98
whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize (#1058)
* add HuggingFace mirror to download  ggml model

* support tdrz via simple hack overriding solm tokens

* fix incorrect translate/transcribe token_ids that are not static const

* add apollo 13 sample for tdrz demo

* render [SPEAKER TURN] consistently in all terminal output using vocab.id_to_token

* extend whisper_segment with speaker_turn_next field and save in json output

* fix failing go build

* slipped in some python syntax whoops

* whisper : finalize tinydiarize support (add flag + fixes)

* whisper : tdrz support for word-level timestamps (respect max_len)

* java : try to fix tests after adding tdrz_enable flag

* main : remove TODO leftover

* java : fix params order list after adding "tdrz_enable"

* whisper : fix solm and add nosp token

* main : print tinydiarize help

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-04 09:45:00 +03:00
Georgi Gerganov
fdf58a6668
talk-llama : fix new rope interface 2023-07-03 19:24:01 +03:00
Georgi Gerganov
8ba42095c5
Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)"
This reverts commit 3f7a03ebe3.
2023-07-02 21:53:52 +03:00
Georgi Gerganov
d6509bf78d
ggml : sync latest repo (mostly refactoring changes) 2023-07-02 21:46:09 +03:00
Przemysław Pawełczyk
85ed71aaec
talk-llama : fix build on macOS (#1062)
* talk-llama : use posix_madvise() instead of madvise() derived from BSD

sed -i 's,\<madvise\>,posix_&,g;s,\<MADV_,POSIX_&,g' examples/talk-llama/llama-util.h

* make : enable Darwin extensions for macOS builds

This is an attempt at fixing macOS build error coming from the fact that
RLIMIT_MEMLOCK define is not available there without Darwin extensions.
2023-06-28 22:34:50 +03:00
thefinaldegree
49c9472fa0
extra : update 'quantize-all.sh' to quantize all downloaded models (#1054)
Script will now do what it says: quantize everything except testing models in the 'models'  directory.
2023-06-28 22:07:02 +03:00
Georgi Gerganov
72deb41eb2
whisper : split_on_word no longer trims (#1046) 2023-06-25 23:51:01 +03:00
Przemysław Pawełczyk
3f7a03ebe3
ggml : do not use _GNU_SOURCE gratuitously (#1027)
* Do not use _GNU_SOURCE gratuitously.

What is needed to build whisper.cpp and examples is availability of
stuff defined in The Open Group Base Specifications Issue 6
(https://pubs.opengroup.org/onlinepubs/009695399/) known also as
Single Unix Specification v3 (SUSv3) or POSIX.1-2001 + XSI extensions.

There is no need to penalize musl libc which simply follows standards.

Not having feature test macros in source code gives greater flexibility
to those wanting to reuse it in 3rd party app, as they can build it with
minimal FTM (_XOPEN_SOURCE=600) or other FTM depending on their needs.

It builds without issues in Alpine (musl libc), Ubuntu (glibc), MSYS2.

* examples : include SDL headers before other headers

This is an attempt at fixing macOS build error coming from SDL2 relying
on Darwin extension memset_pattern4/8/16 coming from Apple's string.h.
2023-06-25 16:34:30 +03:00
Przemysław Pawełczyk
62642bb61c
talk-llama : fix build after ggml sync (#1049)
sed -i 's,GGML_BACKEND_CUDA,GGML_BACKEND_GPU,g' examples/talk-llama/llama.cpp
2023-06-25 16:13:50 +03:00
Georgi Gerganov
f1c9df5806
metal : sync ggml-metal (ref #1047) 2023-06-25 15:40:39 +03:00
Georgi Gerganov
6c25fae1c4
opencl : sync latest ggml-opencl 2023-06-25 15:38:30 +03:00
Philippe Normand
44cb044e66
whisper : fix build with -Werror=undef (#1045) 2023-06-25 15:30:39 +03:00
Simon Moisselin
6c68218e3c
models : add ggml_to_pt script (#1042)
* adding ggml_to_pt

* typo sys too many args

* fixing swap errors dimensions

---------

Co-authored-by: simonMoisselin <simon.moisselin@gmail.com>
2023-06-25 15:29:54 +03:00
Roddur Dasgupta
f11f33f1c0
models : cd statements are quoted to allow spaces in path (#1041) 2023-06-25 15:27:28 +03:00
Georgi Gerganov
8ac23c9f77
models : handle paths with spaces in download script (close #1038) 2023-06-25 15:23:23 +03:00
Colin
14baf2e7f3
main : add diarization support for all current output types (#1031)
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-25 15:07:57 +03:00
GiviMAD
bc2dcf85fe
readme : add java alternative binding (#1029)
Signed-off-by: Miguel Álvarez <miguelwork92@gmail.com>
2023-06-25 14:46:07 +03:00
Jay Binks
1e45911f1a
go : add support for whisper_full_lang_id() (#1010)
* * Add support for whisper_full_lang_id() to go bindings

* Expose token.id so we can test beg, eot etc

---------

Co-authored-by: Jay Binks <jay.binks@overthewire.com.au>
2023-06-25 14:45:33 +03:00
Georgi Gerganov
67564201ec
go : fix "cb" -> "callNewSegment" 2023-06-25 14:34:10 +03:00
Georgi Gerganov
5feb0dffba
ggml : sync latest ggml lib 2023-06-25 14:30:44 +03:00
Bo-Yi Wu
7dfc11843c
go : improve progress reporting and callback handling (#1024)
- Rename `cb` to `callNewSegment` in the `Process` function
- Add `callProgress` as a new parameter to the `Process` function
- Introduce `ProgressCallback` type for reporting progress during processing
- Update `Whisper_full` function to include `progressCallback` parameter
- Add `registerProgressCallback` function and `cbProgress` map for handling progress callbacks

Signed-off-by: appleboy <appleboy.tw@gmail.com>
2023-06-25 14:07:55 +03:00
byte-6174
6a7f3b8db2
make : update cuBLAS build both x86 and aarch64 (#1015)
make cuBLAS compilation compatible with x86 as well as aarch64.
2023-06-25 13:59:48 +03:00
KP Kaiser
207a12f5bc
make : fix for CUDA native not working as an option on Ubuntu (#1012) 2023-06-25 13:57:18 +03:00
faker
26b70395ff
main : exit gracefully when invalid params are passed
* Refactor whisper_params_parse to return false on failure

* Updated help flag behavior
2023-06-25 13:52:29 +03:00
faker
598f607e28
main : gracefully exit when invalid params are passed (#1002)
* Refactor whisper_params_parse to return false on failure

* Updated help flag behavior
2023-06-25 13:51:59 +03:00