Commit Graph

646 Commits (176d7e4e7b7aa03e7c5303f8654cdc7cecf36e8e)

Author SHA1 Message Date
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
Akash Mahajan 3ec7bfffe0
py : make convert-pt-to-ggml.py backwards compatible with older vocab.json tokenizer files (#1001)
* patch checkpoint convert script to keep compatibility with older hf_transformers whisper tokenizer

* typo fix
2023-06-25 13:50:14 +03:00
Larry Battle a7f822ef59
readme : corrected syntax for markdown link (#995) 2023-06-25 13:46:44 +03:00
Nicholas Albion 57543c169e updated java README 2023-06-06 10:27:26 +10:00
Nicholas Albion 5b9e59bc07 `speak` scripts for Windows 2023-06-01 22:45:00 +10:00
Nicholas Albion 3f7436e8a0 updated README for java 2023-06-01 16:55:48 +10:00
geniusnut ce6f747064
whisper.android : support decode wav file has 2 channels (#972) 2023-05-31 10:13:14 +03:00
Nicholas Albion d7c936b44a
Feature/java bindings2 (#944)
* Java needs to call `whisper_full_default_params_by_ref()`, returning struct by val does not seem to work.
* added convenience methods to WhisperFullParams
* Remove unused WhisperJavaParams
2023-05-29 09:38:58 +10:00
genevera (she/her) 9b926844e3
models : fix README.md (#964)
Fixes typo on line 76 of models/README.md
2023-05-27 10:40:28 +03:00
DGdev91 5e2b3407ef
examples : update elevenlabs scripts to use official python API (#837)
* Update elevenlabs example to use ufficial python API

* Update elevenlabs example to use official python API
2023-05-24 21:11:01 +03:00
0xsourcecode 4e16a8fb63
readme : highlight OpenBLAS support (#956)
* highlight openblas support

* Update README.md
2023-05-24 11:23:51 +03:00
Georgi Gerganov 77eab3fbfe
talk-llama : sync latest llama.cpp (close #922, close #954) 2023-05-23 14:04:39 +03:00
Alexey Kharlamov 041be06d58
cmake : build with any BLAS compatible library (#927)
* Build with any BLAS library

* ci: Removed explicit CUDA nvcc path
2023-05-20 21:23:45 +03:00
Georgi Gerganov 429b9785c0
ggml : update WASM SIMD 2023-05-20 20:00:06 +03:00
Georgi Gerganov e410cfc3ce
ggml : sync latest ggml repo
- new Q4 and Q8 quantization
- updated CUDA
2023-05-20 18:56:30 +03:00
Nicholas Albion bc89f285d8
bindings : add java bindings (#931)
* WIP - java bindings

* updated README

* failed attempt at JNI

* fullTranscribe() test passes

* tested on Ubuntu 20

* link to Java bindings
2023-05-20 18:25:02 +03:00
Elkana Bardugo 56a87ba45d
whisper : fix hebrew language code (#935) 2023-05-20 18:17:54 +03:00
Ahmad Bilal 95b02d76b0
coreml : add support of large-v1 model (#926) 2023-05-15 18:36:06 +03:00
Georgi Gerganov a5defbc1b9
release : v1.4.2 2023-05-14 19:06:45 +03:00
Georgi Gerganov aaf0d41c7c
ggml : add AVX dot products 2023-05-14 18:56:46 +03:00
Georgi Gerganov 0cb820e0f9
talk-llama : fix build + sync latest llama.cpp 2023-05-14 18:46:42 +03:00
Jhen-Jie Hong 16564f554f
readme : improve Core ML model conversion guidance (#915) 2023-05-14 18:11:08 +03:00
Georgi Gerganov fd01209d09
coreml : support quantized model files 2023-05-14 18:09:44 +03:00
Georgi Gerganov e693074aa6
ggml : sync latest ggml
- New Q4 and Q5 formats
- Various improvements
2023-05-14 18:04:23 +03:00