4698dcdb52
whisper : add mechanism for aborting the whisper_full() computation
2022-11-27 20:42:45 +02:00
e266cb0723
whisper.objc : add real-time processing ( #97 )
...
Similar to the "stream" app
2022-11-26 18:32:46 +02:00
c207eed431
whisper.objc : fix build warnings
2022-11-26 16:27:04 +02:00
be16dfa038
whisper.wasm : do not block page while processing ( close #86 )
2022-11-25 23:07:42 +02:00
b8ce25dec1
refactoring : more readable code
2022-11-25 19:28:04 +02:00
128aaadb93
whisper : improve printfs
2022-11-24 17:54:16 +02:00
83456076f0
add AVX support
2022-11-23 22:16:33 +02:00
49706a658a
minor : updates few prints + fix buttons in whisper.wasm
2022-11-23 17:19:21 +02:00
385236d1d3
stream : "-kc" now enables context keeping from previous segment ( #90 )
...
By default, the context keeping is disabled
2022-11-22 18:21:15 +02:00
63ae03b8e0
Prompt previous tokens for streaming ( #163 )
...
* feat: prompt previous tokens for streaming
I used a vector pointer instead of vector itself because it gave weird errors, and why not
* convert vector to use with C api
* feat: remove old refs, check for prompt size
* feat: use better way of getting the pointer
2022-11-22 18:10:35 +02:00
a4dfbeecf9
talk.wasm : GPT-2 meets Whisper in WebAssembly ( #155 )
...
* talk : initial real-time transcription in the browser
* talk : polishing the UI
* talk : ready for beta testing
* talk.wasm : rename example
2022-11-21 22:20:42 +02:00
fb8d77f760
stream : add "audio_ctx" parameter
...
Used to overwrite the audio context size of the Encoder.
For example, setting "audio_ctx = 512" will make it run about 3 times
faster, processing about 10s of audio, instead of 30s.
The transcription quality drops, but this can be used for real-time
streaming purposes where performance is important.
2022-11-20 21:22:41 +02:00
62b5ff875c
stream : add "max_tokens" parameter
...
Used to limit the number of tokens in a segment.
Useful to battle with word repetition when using partial encoder context
2022-11-20 21:22:41 +02:00
d351771a4b
stream : add "single_segment" option
...
Force the entire audio chunk to be transcribed into a single segment
2022-11-20 21:22:41 +02:00
c058aaf22e
stream : partial encoder experiments
2022-11-20 21:22:41 +02:00
2ba66360c9
fix: free ggml_context ( close #149 ) ( #150 )
...
* fix: free ggml_context
* ggml : free the model's contexts in whisper_free()
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2022-11-17 22:12:51 +02:00
83c742f1a7
whisper : add option to speed up the audio tempo by x2
...
Using a Phase Vocoder for speeding up the audio tempo by scaling down
the frequencies in the frequency domain.
This reduces the computation in the Encoder by a factor of 2.
The transcription accuracy is degraded, but for slow to normal speech -
it seems to be still very good.
I think this can find application for real-time transcription - i.e. the
"stream" example.
2022-11-13 16:25:43 +02:00
c30bffc8a5
ref #22 : add "duration" option
...
Can be used to partially process a recording
2022-11-07 20:14:52 +02:00
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
2022-11-02 21:45:54 +02:00
02dfd5b8c3
whisper : fix extra memory usage after recent processor changes
...
Had increased the memory buffer to the size of the model and forgot to
bring it down.
2022-11-02 18:31:18 +02:00
57fb46f307
main : add option for word-leve timestamps (very experimental)
2022-10-30 17:06:57 +02:00
eba62e0fa1
close #113 : fix struct whisper_token_data
2022-10-30 08:23:52 +02:00
014a119052
minor : fix multiple definitions of to_timestamp()
2022-10-29 19:37:19 +03:00
dec40be58f
parallel : print time of audio boundaries + fix timings
2022-10-29 19:37:19 +03:00
0b2dc3c82c
parallel : working
2022-10-29 19:37:19 +03:00
85d6e1e1e7
main : fix sampling time + add max_context parameter
2022-10-29 19:37:19 +03:00
72e9cdd6bf
parallel : adding tool for parallel transformer inference
2022-10-29 19:37:19 +03:00
c565c569e7
Define WHISPER_BUILD so as to export symbols on Windows
2022-10-29 13:23:09 +03:00
34bb3ab0cf
ggml : add system info functions
2022-10-25 20:53:48 +03:00
5f7e9fa2dc
ref #68 , #79 : fix segment time output
2022-10-23 13:30:30 +03:00
7affd309d3
whisper : add new-segment callback
...
Can be used to process new segments as they are being generated.
Sample usage in main, for printing the resulting segments during the
inference.
2022-10-22 21:17:21 +03:00
31ff0c6a1f
wip : experimental color coding of tokens based on probabilities
2022-10-22 21:17:21 +03:00
8d15a1c635
ci : fix and re-enable tests (2nd try)
2022-10-21 15:57:20 +03:00
692aa0784f
Revert "ci : fix and re-enable tests"
...
This reverts commit 80aefc9514
2022-10-21 15:36:19 +03:00
80aefc9514
ci : fix and re-enable tests
2022-10-21 15:27:30 +03:00
7eeef0358a
ref #52 : improve greedy sampling strategy
...
Force timestamp token to be sampled if the probability sum over all
timestamp tokens is above the probability of any other token
2022-10-18 19:48:15 +03:00
e30cf83158
ref #57 , #62 , #63 : remove unions in C-api + remove designated initializers
...
We are not ready for designated initializers - many compilers do not
support this C++ feature yet, so removing it's non-trivial usages.
2022-10-18 18:17:24 +03:00
d6b84b2a23
ref #62 : fix build for some compilers
...
For some reason, new version of GCC panic when the struct type is not
specified explicitly
2022-10-18 10:57:03 +03:00
b4a3875b2c
Revert recent sampling change
...
It does not actually help and seems to produce worse results on some of
the samples
2022-10-18 08:26:16 +03:00
cf67bfffa0
Fix EOT token handling
...
If it is the end of the audio, pick all sampled tokens.
Otherwise, print error message.
2022-10-18 00:53:06 +03:00
d14823582d
Try to improve the sampling strategy a bit
...
It sill fails sometimes when it does not sample a timestamp token for
the entire segment. We now print a message in such cases
2022-10-18 00:12:51 +03:00
20d8e7a309
Fix memory sizes
2022-10-18 00:12:51 +03:00
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
2022-10-18 00:12:51 +03:00
0ad085f5e8
ref #48 : clear results at the start of whisper_full
...
This way, even if the input audio is empty, the previous results will be
removed.
2022-10-15 09:55:28 +03:00
b799226973
check if spectogram length is <100 before doing anything else
...
fixes #39
2022-10-12 07:32:42 +03:00
0b45d25151
Building with MSVC
2022-10-11 21:40:46 +03:00
63b6786767
Minor
2022-10-10 22:06:27 +03:00
4bbb8a587b
Add MinGW support
2022-10-09 22:26:37 +08:00
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.
2022-10-08 17:28:06 +03:00
8c7c018893
ref #17 : add options to output result to file
...
Support for:
- plain text
- VTT
- SRT
2022-10-08 17:22:22 +03:00
