864a78a8d0
models : change default hosting to Hugging Face
...
My Linode is running out of monthly bandwidth due to the big interest in
the project
2 years ago
8fdfb0ba92
Update README.md
2 years ago
a09e9123ca
Update README.md
2 years ago
0e689f83d8
Update README.md
2 years ago
d5afebd37c
whisper : token-level timestamp refactoring ( #49 , #120 )
...
This turned out pretty good overall. The algorithm has been moved from
main.cpp to whisper.cpp and can be reused for all subtitles types. This
means that now you can specify the maximum length of the generated
lines. Simply provide the "-ml" argument specifying the max length in
number of characters
2 years ago
4b1c32e8ea
Update README.md
2 years ago
b5dde365e9
extra : compute SHA of all models files
2 years ago
e46bc56e71
Update README.md
2 years ago
b0f2aa0ea6
Update README.md
2 years ago
2c281d190b
Update README.md
2 years ago
9ccafa8792
Update README.md
2 years ago
89d8ee3ee5
Update README.md
2 years ago
c6710efde2
refactoring : move main + stream in examples + other stuff
2 years ago
728676927f
Update README.md
2 years ago
181b762de8
Update README.md
2 years ago
4196856c7b
Update README.md
2 years ago
705198f063
Update README.md
2 years ago
3e69a6071d
Update README.md
2 years ago
f3dae90c31
Update README.md
2 years ago
8c1d970088
Update README.md
2 years ago
6b45e37b2b
Update README.md and finalize the whisper.wasm example
2 years ago
5698b51718
Update README.md
2 years ago
3fe3898ebb
Update README.md
2 years ago
81c185576c
Update README.md
2 years ago
1969ee4bc7
Update README.md
2 years ago
72d967bce4
Use Accelerate framework on Apple silicon
...
Huge performance improvement in the Encode (almost x2 on MacBook M1 Pro)
Also various extra optimizations:
- Multi-threaded NORM operator
- Faster GELU via F16 cast
2 years ago
36945162fa
Update README.md (ref #50 )
2 years ago
b2f1600aa3
Update README.md
2 years ago
1348796a93
Update README.md ( #43 )
...
* Update README.md
Updated README.md to list new features, such as subtitle file support (VTT and SRT)
* Update README.md
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2 years ago
8d94358251
Update README.md
2 years ago
ad6693fb64
Update README.md
2 years ago
63b6786767
Minor
2 years ago
f7ab81fe51
Update README.md
2 years ago
4c4ab71d4d
Update README.md
2 years ago
2d47693435
Update README.md
2 years ago
700898e6ed
ref #22 : add option to provide multiple input .wav files
2 years ago
6b1c3cc198
Update README.md
2 years ago
b8f713482e
Minor updates
2 years ago
e7a15876f8
Update README.md
2 years ago
d71e567656
Update README.md
2 years ago
62897e8ae6
Update README.md
2 years ago
3bcdbdfc32
Reduce memory usage even more + better sampling
...
- The encode/decode memory buffers are now reused
- If the 30-sec segment goes for too long without a timestamp token, we
force one. Improves transcription for large model
- Stereo support
- Add "micro-machines.wav" sample
2 years ago
310f4883d1
Update README.md
2 years ago
fd3f3d748f
Update README.md
2 years ago
5877c3578e
ref #4 : added transcription timestamps
...
Can be turned off with "-nt" argument.
Performance has also improved.
2 years ago
4352a6018b
Update README.md
2 years ago
f888c2373d
Flash + language support (ref #2 )
...
- Achieved big performance improvement + memory usage reduction
- Can now translate / transcribe different languages
2 years ago
476182e439
Update README.md and simplify usage
2 years ago
f2456f8d93
Create README.md
2 years ago
Georgi Gerganov