04a16bbf11
fix compilation on haiku
1 year ago
47afb93c3c
yt-wsp.sh : improve usage instructions
1 year ago
575c53dc41
yt-wsp.sh : fix usage instruction + comment
1 year ago
3996ecc156
Update README.md
1 year ago
faa85f9840
livestream.sh : remove obsolete comment
1 year ago
b6597539f9
ggml : fix typo in previous commit
1 year ago
9a4b7a916e
ggml : use macros to inline FP16 <-> FP32 conversions
1 year ago
f8ec718b76
ggml : add F16C CPU flag check
1 year ago
35b40a93b9
add fp16/fp32 convert intrinsics
1 year ago
9fe7306f4b
models : add the new "large" model release by OpenAI
...
The old "large" model is now renamed "large-v1".
If you have been using it, make sure to rename it and download the new
"large" model for best results.
1 year ago
13e8eb2346
bench : add commit hash to bench-all.sh results
1 year ago
78d13257be
Try to improve the token sampling strategy ( #193 )
...
* whisper : try to improve the token sampling strategy
- Add the "max_initial_timestaamp" token logic from OpenAI
- Disallow sampling timestamps that are in the past
* whisper : fix the max initial timestamp logic + fallback decoding
1 year ago
9b7df68753
tests : adding transcription tests
1 year ago
061fc81bd6
ggml : remove inline specifier from fp16 <-> fp32 converters
1 year ago
57e0e6b700
livestream : handle ffmpeg errors gracefully and stabilize transcript
1 year ago
4f7363077f
livestream : minor changes
1 year ago
093c840dee
livestream : fix losing words across audio chunk ( #195 )
...
* improve livestream script
* Update examples/livestream.sh
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Paul Edwards <paul.edwards@semiformal.net>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 year ago
e7f09a0a61
Fix Darwin flags - was incorrectly always using the Linux else clause
1 year ago
4698dcdb52
whisper : add mechanism for aborting the whisper_full() computation
1 year ago
6fd5358dd0
Update README.md
1 year ago
164df0d447
whisper.objc : fix context + broken readme links
1 year ago
e266cb0723
whisper.objc : add real-time processing ( #97 )
...
Similar to the "stream" app
1 year ago
c207eed431
whisper.objc : fix build warnings
1 year ago
67e819baf4
minor : remove "examples/" prefix from the README
1 year ago
a425365b82
yt-wsp.sh : script to easily transcribe VODs
...
Thanks to @DaniruKun
ref: https://gist.github.com/DaniruKun/96f763ec1a037cc92fe1a059b643b818
Usage:
cd whisper.cpp
make
./examples/yt-wsp.sh <video-url>
1 year ago
e0e864d9ca
Update README.md
1 year ago
68ecadbbc9
command.wasm : add voice assistant example for the Web ( #171 )
...
Same as the command-line tool "command", but runs in the browser
Also, added helper script "extra/deploy-wasm.sh" and fixed some timing
constants for the WASM examples.
1 year ago
c536ff4005
minor : add comment for using "generate_karaoke.sh"
1 year ago
cb70b07db5
livestream.sh : simple tool to transcribe audio livestreams ( #185 )
1 year ago
3c390ffe38
stream.wasm : add web-based real-time transcription ( #112 )
1 year ago
be16dfa038
whisper.wasm : do not block page while processing ( close #86 )
1 year ago
0f619b52ce
main : add stereo-channel-based diarization ( #64 )
...
Not tested - I don't have stereo dialog audio
1 year ago
1246dd023e
command : add demonstration video
1 year ago
0be27bbd92
command : fix build + fix README + add bold printing
1 year ago
bc88eb13c6
examples : add "command" tool ( #171 )
1 year ago
b8ce25dec1
refactoring : more readable code
1 year ago
fd113687aa
correct model name display on running samples
1 year ago
e4805d9601
wasm : refactor wasm example + reuse fetch mechanism
1 year ago
ff36415a86
talk.wasm : update video link + some minor fixes
1 year ago
025ff465b6
Update README.md
...
Use a less cringy video to demo talk.wasm lol
1 year ago
2c0501b38a
Update README.md
1 year ago
abce28ea99
talk.wasm : move to https://whisper.ggerganov.com/talk
...
This way, we can share the same models across different WASM examples
and not have to download them for each page
1 year ago
a2ecd54455
models : add instructions for using HF fine-tuned models
1 year ago
128aaadb93
whisper : improve printfs
1 year ago
454b91de16
main : fix dangling pointer when using stdin for input ( #65 )
1 year ago
d7024cf9dc
main, stream : remove --verbose flag ( #178 )
1 year ago
37422ed733
talk.wasm : add audio pre-processing + bump memory
1 year ago
be3b720f96
talk.wasm : refactoring + update README.md
1 year ago
00f46dbc1d
models : add usage comments to the HF convert script ( #157 )
1 year ago
5698bddbc9
models : fix HF fine-tuned model conversion script ( #157 )
...
It works now
1 year ago
Al Hoang
Georgi Gerganov
katsu560
semiformal-net
Tienshiao Ma
vicalloy