f897eb7670
whisper : support no_speech_thold ( #2625 )
...
* Implement no_speech_thold
no_speech_thold functionality is on par with OpenAI's whisper
* Addressed review comments
2024-12-17 19:15:47 +02:00
2f2841bfce
whisper : add single-timestamp logic ( #2629 )
...
* Fix hallucinations during silence
When the predicted tokens end with a single timestamp the the entire 30 segment should be considered as done, to avoid hallucinations for the remaining part of segment.
This behaviour is on par with openai's whisper. Refer to logic related to `single_timestamp_ending` in https://github.com/openai/whisper/blob/main/whisper/transcribe.py
* Accept review comments related to formatting.
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-12-17 19:07:08 +02:00
37c88027e1
whisper : use backend registry ( #0 )
2024-11-20 21:00:08 +02:00
7fd8d9c220
whisper : adapt to new ggml (wip)
2024-11-20 21:00:08 +02:00
5089ab2d6a
whisper : fix build ( #0 )
2024-11-15 15:21:04 +02:00
5f8a086e22
whisper.swiftui : add model download list & bench methods ( #2546 )
...
* swift : fix resources & exclude build
* whisper : impl whisper_timings struct & api
* whisper.swiftui : model list & bench methods
* whisper : return ptr for whisper_get_timings
* revert unnecessary change
* whisper : avoid designated initializer
* whisper.swiftui: code style changes
* whisper.swiftui : get device name / os from UIDevice
* whisper.swiftui : fix UIDevice usage
* whisper.swiftui : add memcpy and ggml_mul_mat (commented)
2024-11-13 21:51:34 +02:00
5ccca19f0c
ggml : vulkan logs ( #2547 )
2024-11-13 21:47:15 +02:00
31aea563a8
whisper : fix extra memory usage ( #2534 )
...
* passing samples_padded by ref to the threads.
* passing samples_padded by ref to the threads.
---------
Co-authored-by: Vinith Misra <physicsdemon@gmail.com>
2024-11-06 23:02:11 +02:00
0377596b77
whisper : backend registry init before model load
2024-11-01 10:19:05 +02:00
aa037a60f3
ggml : alloc ggml_contexts on the heap ( #2525 )
...
* whisper : reduce ggml_context usage
* ggml : allocate contexts on the heap (v2)
* ggml : aligned malloc -> malloc
2024-10-31 22:00:09 +02:00
3f020fac9d
whisper : minor compile warning
2024-10-29 19:30:26 +02:00
1626b73b03
whisper : move new-segment callback after DTW step ( #2515 )
2024-10-29 08:47:21 +02:00
0fbaac9c89
whisper : fix index overflow in token-level timestamp logic ( #2505 )
2024-10-23 15:14:03 +03:00
b6049060dd
whisper : add dtw preset for large-v3-turbo ( #2481 )
2024-10-15 21:00:21 +03:00
fdbfb460ed
whisper : add OpenVINO init with state ( #2464 )
...
* Fixed OpenVino init on state
* Removed an empty line
* Fixed typo
* Replaced tabs with spaces
---------
Co-authored-by: Sandro Hanea <sandrohanea@users.noreply.github.com>
2024-10-08 20:08:00 +03:00
847f94fdeb
whisper : zero-out the KV cache upon clear ( #2445 )
2024-10-05 15:23:51 +03:00
396089f3cf
whisper : revert mel-related changes ( #0 )
...
too much extra logic and complexity for small benefit
2024-10-05 15:23:51 +03:00
941912467d
whisper : adapt to latest ggml (skip) ( #0 )
2024-10-05 15:23:51 +03:00
f62a546e03
whisper : fix excessive memory usage ( #2443 )
...
* whisper : fix KV cache allocation
* whisper : reduce memory overhead from unused input tensors
2024-10-05 12:36:40 +03:00
ccc2547210
talk-llama : sync llama.cpp
2024-10-03 12:22:17 +03:00
fe18c29ab8
talk-llama : sync llama.cpp
2024-09-24 19:45:08 +03:00
34291099fb
ggml : refactoring (llama/#0)
...
- d6a04f87
- 23e0d70b
2024-09-24 19:45:08 +03:00
9d754a56cf
whisper : update FA call
2024-08-28 13:22:20 +03:00
6e9596f6de
whisper : fix compile warning for unused params
2024-08-28 11:40:11 +03:00
81c999fe0a
cann : add Ascend NPU support ( #2336 )
...
* enable Ascend NPU in src/whisper.cpp
* sync test-backend-ops with llama.cpp
2024-08-09 15:21:56 +03:00
4b7de08bfd
whisper : fix compile warning ( #0 )
2024-08-09 09:58:16 +03:00
fe36c90971
cmake : fix compile in xcode ( #2311 )
2024-08-05 09:48:26 +03:00
6739eb83c3
whisper : handle empty mel ( #2324 )
2024-07-27 20:35:04 +03:00
f68298ce06
whisper : use vulkan as gpu backend when available ( #2302 )
...
* ggml: use vulkan as gpu backend when available
Signed-off-by: Matt Stephenson <mstephenson6@users.noreply.github.com>
* whisper: enable using vk as default buffer type
Signed-off-by: Matt Stephenson <mstephenson6@users.noreply.github.com>
---------
Signed-off-by: Matt Stephenson <mstephenson6@users.noreply.github.com>
2024-07-16 10:21:09 +03:00
7ae885c1ef
whisper : fix DTW assert ( #2299 )
2024-07-15 15:50:36 +03:00
d207c68822
cmake : use WHISPER_EXTRA_FLAGS ( #2294 )
2024-07-09 18:54:18 +03:00
1c31f9d4a8
cmake : try to fix openvino build ( #2281 )
2024-07-08 15:36:51 +03:00
dbf9c15e30
talk-llama : sync llama.cpp
2024-07-08 14:53:55 +03:00
dc8cc2dd6f
whisper : disable CUDA mel + fix FFMPEG
2024-06-26 20:11:38 +03:00
e30c679928
whisper : reorganize source code + improve CMake ( #2256 )
...
* scripts : update sync [no ci]
* files : reorganize [no ci]
* sync : llama.cpp
* cmake : link math library
* cmake : build normal ggml library
* files : move headers to include
* objc : fix path to ggml-metal.h
* ci : fix WHISPER_CUDA -> GGML_CUDA
* scripts : sync LICENSE [no ci]
2024-06-26 19:34:09 +03:00
820446e230
fix : remove extra files
2024-06-18 09:39:40 +03:00
de29b193f6
move BLAS to a separate backend (cont) (llama/6210)
...
ggml-ci
2024-06-18 09:39:40 +03:00
Karthick
Georgi Gerganov
Jhen-Jie Hong
thewh1teagle
Vin Misra
jettoblack
Josscii
Rotem Dan
Sandro Hanea
Mengqing Cao
Daven Sanassy
Matt Stephenson
arizhih
slaren