Georgi Gerganov 7094ea5e75

whisper : use flash attention (#2152) ...

* whisper : use flash attention in the encoder

* whisper : add kv_pad

* whisper : remove extra backend instance (huh?)

* whisper : use FA for cross-attention

* whisper : use FA for self-attention

* whisper : simplify encoder FA

* whisper : add flash_attn runtime parameter

* scripts : add bench log

* scripts : add M1 Pro bench log

2024-05-15 09:38:19 +03:00

..

addon.node

node : add audio_ctx and audio buffer params (#2123)

2024-05-13 15:22:23 +03:00

bench

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

bench.wasm

whisper : add support for large v3 (#1444)

2023-11-07 15:30:18 +02:00

command

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

command.wasm

whisper : add context param to disable gpu (#1293)

2023-11-06 11:04:24 +02:00

lsp

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

main

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

python

examples : add python example for transcription (#1744)

2024-01-13 19:37:18 +02:00

quantize

quantize : fix load vocab crash when len is 128 (#1160)

2023-08-06 11:04:42 +03:00

server

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

stream

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

stream.wasm

stream.wasm : fix invalid memory access when no segments (#1902)

2024-02-26 10:12:35 +02:00

sycl

whisper : add SYCL support (#1863)

2024-02-23 09:22:24 +02:00

talk

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

talk-llama

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

talk.wasm

examples : clean up common code (#1871)

2024-02-19 10:50:15 +02:00

wchess

whisper : use flash attention (#2152)

2024-05-15 09:38:19 +03:00

whisper.android

whisper.android : update example, add field to print timestamp (#2072)

2024-05-13 14:30:03 +03:00

whisper.android.java

whisper.android.java : fix returns in JNI (#1929)

2024-03-05 15:59:26 +02:00

whisper.nvim

whisper.nvim : fix missing reference to "model" variable (#2049)

2024-04-15 19:41:28 +03:00

whisper.objc

docs : make model options / model install methods clearer (#1806)

2024-01-26 17:39:54 +02:00

whisper.swiftui

whisper.swiftui : add .gitignore

2024-01-04 15:00:27 +02:00

whisper.wasm

whisper : add context param to disable gpu (#1293)

2023-11-06 11:04:24 +02:00

CMakeLists.txt

cmake : fix json INTERFACE library (#2069)

2024-05-13 14:29:39 +03:00

common-ggml.cpp

ggml : resolve merge (ggml/0)

2024-05-13 11:02:26 +03:00

common-ggml.h

whisper : add integer quantization support (#540)

2023-04-30 18:51:57 +03:00

common-sdl.cpp

sdl : fix audio callback (#1523)

2023-11-20 13:16:38 +02:00

common-sdl.h

sdl : fix audio callback (#1523)

2023-11-20 13:16:38 +02:00

common.cpp

common : fix file-handle leak in read_wav() (#2026)

2024-04-09 18:34:34 +03:00

common.h

talk, talk-llama : pass text_to_speak as a file (#1865)

2024-02-24 09:24:47 +02:00

dr_wav.h

refactoring : move main + stream in examples + other stuff

2022-10-25 20:53:48 +03:00

generate-karaoke.sh

minor : add comment for using "generate_karaoke.sh"

2022-11-26 10:22:42 +02:00

grammar-parser.cpp

whisper : update grammar-parser.cpp (#2058)

2024-04-15 19:40:27 +03:00

grammar-parser.h

whisper : add grammar-based sampling (#1229)

2023-11-13 10:51:34 +02:00

helpers.js

js : remove un-needed request header from fetchRemote (#2119)

2024-05-13 15:13:19 +03:00

json.hpp

examples : clean up common code (#1871)

2024-02-19 10:50:15 +02:00

livestream.sh

whisper : make large version explicit + fix data size units (#1493)

2023-11-15 19:42:25 +02:00

twitch.sh

whisper : make large version explicit + fix data size units (#1493)

2023-11-15 19:42:25 +02:00

yt-wsp.sh

yt-wsp.sh : print help on empty args

2023-02-18 09:42:31 +02:00