f3ee4a9673
whisper : reduce memory usage during inference ( #431 )
...
* ggml : add "scratch" buffer support
* ggml : support for scratch ring-buffer
* ggml : bug fix in ggml_repeat()
* ggml : error on scratch buffer overflow
* whisper : use scratch buffers during inference (base model only)
* whisper : update memory usage for all models
* whisper : fix encoder memory usage
* whisper : use whisper_context functions instead of macros
* whisper : fix FF + remove it from README
* ggml : reuse ggml_new_i32
* ggml : refactor the scratch buffer storage
* whisper : reorder scratch buffers in the decoder
* main : add option to disable temp fallback
* Update README.md
1 year ago
2c3f50a021
release : v1.1.1
1 year ago
874bde887e
Update README.md
1 year ago
8738427dd6
cmake : bump version to 1.1.0
1 year ago
0b85e8c401
Update README.md
1 year ago
8de452c18b
Improve decoding ( #291 )
...
* whisper : prepare infra for new decoding strategies
* whisper : apply logit filters and compute logprobs
* whisper : add whisper_get_logits()
* whisper : separate self and cross attention memory
Initial step needed for supporting parallel decoders
* whisper : move probs_id buffer to whisper_context
* whisper : refactor kv cache into separate struct
* whisper : move self-attention kv cache to whisper_decoder
* whisper : wip decoding parameters + strategies
* whisper : wip decoding parameters + strategies (part 2)
* whisper : wip decoding parameters + strategies (part 3)
* whisper : wip decoding parameters + strategies (part 4)
* whisper : fix prompt_past update to not include prompt_init
* whisper : temperature + best_of support
* whisper : support for compression_ration_threshold
We actually use entropy, but it is similar
* command : fix example to use logits instead of obsolete probs
* whisper : handle empty sequence ranking
* whisper : add WHISPER_DEBUG + diagnostic prints + new main args
* whisper : minor fixes
* whisper : add beam-search support
* whisper : bug fix when there no previous context
* whisper : add comments
* stream : disable temperature fallback
For real-time processing, we always want a single decoder running at T=0
* whisper.swiftui : update example - fix paths + add empty folders
1 year ago
5e9f33596f
readme : clarify main and stream usage ( #391 )
...
Give an example of ./main that uses a sample file that's already there, and make the stream example clarify you need `make stream`
1 year ago
1944e7c33e
whisper : document POWER VSX support
1 year ago
1480a5f1af
Update README.md
...
Add SwiftUI example links
1 year ago
4c1fe0c813
Update README.md
...
Add bindings links / discussions
1 year ago
afe2db0fe2
Add Roadmap
1 year ago
ea19ed33f1
Update README.md ( #46 )
...
Add references to the new Android app
1 year ago
c37c2443c1
Update README.md ( #56 )
1 year ago
812ae3ffbd
Update README.md
1 year ago
fcf515de60
bench.wasm : same as "bench" but runs in the browser ( #89 )
1 year ago
3b1aacbe6d
talk : talk with AI in the terminal
1 year ago
3996ecc156
Update README.md
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
6fd5358dd0
Update README.md
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
1246dd023e
command : add demonstration video
1 year ago
bc88eb13c6
examples : add "command" tool ( #171 )
1 year ago
b8ce25dec1
refactoring : more readable code
1 year ago
2c0501b38a
Update README.md
2 years ago
35cd29ce1f
ggml : fix cross-compile Linux -> Window with mingw ( #168 )
2 years ago
a156a358ca
Revert "update README.md"
...
This reverts commit 6a84147113
2 years ago
6a84147113
update README.md
2 years ago
363a2dadec
Update README.md
2 years ago
623a486056
Update README.md
2 years ago
2e311a2917
Update README.md
2 years ago
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
Georgi Gerganov
Ian Bicking
Thomas Fitzsimmons
katsu560