Georgi Gerganov
|
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
|
2 years ago |
|
Georgi Gerganov
|
054940e1f6
|
minor : fix .gitignore to not ignore examples
|
2 years ago |
|
Georgi Gerganov
|
3b1aacbe6d
|
talk : talk with AI in the terminal
|
2 years ago |
|
Georgi Gerganov
|
832b4f34c9
|
make : indentation + .gitignore
|
2 years ago |
|
Georgi Gerganov
|
bc88eb13c6
|
examples : add "command" tool (#171)
|
2 years ago |
|
Georgi Gerganov
|
b8ce25dec1
|
refactoring : more readable code
|
2 years ago |
|
Georgi Gerganov
|
c6710efde2
|
refactoring : move main + stream in examples + other stuff
|
2 years ago |
|
Georgi Gerganov
|
bb1ee266d2
|
ios : whisper.objc example
|
2 years ago |
|
Georgi Gerganov
|
d6b84b2a23
|
ref #62 : fix build for some compilers
For some reason, new version of GCC panic when the struct type is not
specified explicitly
|
2 years ago |
|
Georgi Gerganov
|
b4a3875b2c
|
Revert recent sampling change
It does not actually help and seems to produce worse results on some of
the samples
|
2 years ago |
|
Georgi Gerganov
|
0e858f080d
|
close #56 : build on FreeBSD
Thanks to @abelbabel for the contribution
|
2 years ago |
Borislav Stanimirov
|
28252352d7
|
Visual Studio ignored dirs
|
2 years ago |
|
Georgi Gerganov
|
2f069335ab
|
Adding sanitizer tests
|
2 years ago |
|
Georgi Gerganov
|
877c058179
|
Add CMake support
|
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
|
b0a11594ae
|
Initial release
|
2 years ago |
