Georgi Gerganov
|
8d94358251
|
Update README.md
|
2 years ago |
Georgi Gerganov
|
ad6693fb64
|
Update README.md
|
2 years ago |
Georgi Gerganov
|
01c9e96f64
|
stream : improve real-time transcription
|
2 years ago |
Georgi Gerganov
|
63b6786767
|
Minor
|
2 years ago |
Georgi Gerganov
|
f7ab81fe51
|
Update README.md
|
2 years ago |
Georgi Gerganov
|
eac4f12777
|
Merge pull request #36 from Topping1/master
Fix SRT timestamp format from mm:ss.sss to hh:mm:ss.sss
|
2 years ago |
Georgi Gerganov
|
9d5723435f
|
ref #35 : add <stdbool.h> to whisper.h
"bool" type is not implicitly defined for some compilers.
|
2 years ago |
Georgi Gerganov
|
6e29d8453c
|
Merge pull request #34 from tazz4843/master
Add static library make target
|
2 years ago |
Topping1
|
50b5fe964c
|
Update main.cpp
|
2 years ago |
0/0
|
64752acd27
|
add static library make target
|
2 years ago |
Georgi Gerganov
|
7edaa7da4b
|
Merge pull request #31 from lkwq007/master
Add MinGW support
|
2 years ago |
lnyan
|
4bbb8a587b
|
Add MinGW support
|
2 years ago |
Georgi Gerganov
|
4a6bf11db3
|
Minor
|
2 years ago |
Georgi Gerganov
|
9bbca3110f
|
ref #9 : add API documentation in whisper.h
|
2 years ago |
Georgi Gerganov
|
5e563ef635
|
Fix Makefile for MacBook Intel
|
2 years ago |
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.
|
2 years ago |
Georgi Gerganov
|
8c7c018893
|
ref #17 : add options to output result to file
Support for:
- plain text
- VTT
- SRT
|
2 years ago |
Georgi Gerganov
|
4c4ab71d4d
|
Update README.md
|
2 years ago |
Georgi Gerganov
|
b43b36e006
|
Update tests
|
2 years ago |
Georgi Gerganov
|
37110d693e
|
ci : add base model tests to GH Actions
|
2 years ago |
Georgi Gerganov
|
2d47693435
|
Update README.md
|
2 years ago |
Georgi Gerganov
|
a53e06757f
|
Create README.md
|
2 years ago |
Georgi Gerganov
|
0e3ba2f9fc
|
Adding dummy models for testing purposes
|
2 years ago |
Georgi Gerganov
|
2f069335ab
|
Adding sanitizer tests
|
2 years ago |
Georgi Gerganov
|
29b041f79b
|
Cleanup CMakeLists.txt
|
2 years ago |
Georgi Gerganov
|
4a732b2879
|
cmake : fixes
|
2 years ago |
Georgi Gerganov
|
68f5962be6
|
ci : add cmake builds
|
2 years ago |
Georgi Gerganov
|
332c9d77fe
|
whisper : fix bug in token sampling logic
Could overflow buffer
|
2 years ago |
Georgi Gerganov
|
877c058179
|
Add CMake support
|
2 years ago |
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
|
2 years ago |
Georgi Gerganov
|
3f15bb8a08
|
ref #10 : add "step" argument for "stream" example
Controls how often we run the inference.
By default, we run it every 3 seconds.
|
2 years ago |
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.
|
2 years ago |
Georgi Gerganov
|
e29a5dacc6
|
ref #11, #18, #26 : fix CACHE_LINE_SIZE constant
|
2 years ago |
Georgi Gerganov
|
844d60b284
|
Add CI using Github Actions
|
2 years ago |
Georgi Gerganov
|
700898e6ed
|
ref #22 : add option to provide multiple input .wav files
|
2 years ago |
Georgi Gerganov
|
6b1c3cc198
|
Update README.md
|
2 years ago |
Georgi Gerganov
|
b8f713482e
|
Minor updates
|
2 years ago |
Georgi Gerganov
|
167324584b
|
wip : rpi4 support
|
2 years ago |
Georgi Gerganov
|
ce1fe95902
|
wip : improve makefile
|
2 years ago |
Georgi Gerganov
|
74197ffc11
|
Merge pull request #20 from ArtyomZemlyak/master
Fix: main get language from cli args
|
2 years ago |
Артём Земляк
|
495b81b367
|
Fix: main get n_threads from cli
|
2 years ago |
Артём Земляк
|
f007e186fe
|
Fix: main get language from cli args
|
2 years ago |
Georgi Gerganov
|
e7a15876f8
|
Update README.md
|
2 years ago |
Georgi Gerganov
|
6814cc9b02
|
Improve result printing
|
2 years ago |
Georgi Gerganov
|
eba33adadd
|
Extend C-style API with full inference methods
|
2 years ago |
Georgi Gerganov
|
6b77124e01
|
Initial C-style interface for whisper.cpp
|
2 years ago |
Georgi Gerganov
|
be8ba034f6
|
ref #10 : handle Ctrl+C in "stream" app
|
2 years ago |
Georgi Gerganov
|
d71e567656
|
Update README.md
|
2 years ago |
Georgi Gerganov
|
b6bf906730
|
ref #10 : quick-and-dirty attempt for real-time audio transciption
- Processes input in chunks of 3 seconds.
- Padding audio with silence
- Uses 1 second audio from previous pass
- No text context
|
2 years ago |
Georgi Gerganov
|
77d929f603
|
Fix bug in FFT
The FFT routine does not work for odd N
Solution is to add DFT and use it when N is odd
|
2 years ago |