Commit Graph

83 Commits (master)

Author SHA1 Message Date
Georgi Gerganov 1558ec5a16
whisper : improve handling of prompts (#1981)
* whisper : improve handling of prompts

* whisper : add whisper_token_count helper
2024-03-25 14:48:19 +02:00
denersc 741abb162c
whisper : token-level timestamps with DTW (#1485)
* whisper.cpp: impl dtw algo

* WIP: producing and placing DTW timestamps on tokens

* Fix compile and assertion errors. Attempt to DTW timestamp with single_segment=false.

* Fix mistake causing incorrect alignment of dtw timestamps

* implement N_TOP_MOST and CUSTOM alignment heads setting

* whisper: fix typo on alignment heads enum

* Fix issues related to changes in whisper.cpp

* Fixed excessive memory use when using DTW timestamps. Other minor fixes to DTW timestamping function

* decoder: save cross QKs only if requested

* Calling median filter with ggml_map_custom1

* Reimpl aheads n_top_most and custom. Sanity checks on chosen aheads

* Copying cross QKs from decoder backend correctly

* dtw: cleanup

* Fix incorrect n_frames passed to dtw when near end of audio

* Fix aheads_masks_init for backend != CPU

* whisper : minor style

* main : add dtw (wip)

* whisper: fix invalid memory access in aheads_masks_init

* main : add dtw (cont)

* whisper : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-20 18:25:26 +02:00
Jo Liss e7794a868f
examples : rename --audio-context to --audio-ctx per help text (#1953) 2024-03-18 17:53:33 +02:00
F1L1P 2e2626b167
examples : Auto lowercase language parameter in main.cpp (#1928)
* Auto lowercase language parameter

* Update examples/main/main.cpp

Co-authored-by: bobqianic <129547291+bobqianic@users.noreply.github.com>

---------

Co-authored-by: bobqianic <129547291+bobqianic@users.noreply.github.com>
2024-03-06 22:25:10 +00:00
Davidson Francis c56344b509
main : fix file existence check in main.cpp (#1889)
In commit dda4b0e of PR #1872, I've introduced a check for the
existence of files before loading the model. However, I haven't
considered the case where whisper.cpp might read from stdin as well,
and in such cases, the checks should ignore the "-" argument as it
does not represent a regular file.

Additionally, this commit removes the usage of 'stat()' in favor of
the recently introduced function 'is_file_exist()' in common.cpp from
PR #1871.

Apologies for the bug introduced in the previous PR and any
inconvenience it may have caused.
2024-02-22 15:01:08 +02:00
Davidson Francis dda4b0ed06
main : check if input files exist before proceeding (#1872)
Until the most recent commit (3d42463), the main.cpp sample file does
not check whether the input files exist or not. Consequently, the
model is loaded first before reporting whether there was a failure or
not when processing a file. In environments with HDD, this can take
about 50 seconds or more, depending on the loaded model.

This commit addresses this issue by checking in advance whether the
input files exist or not.
2024-02-19 10:51:26 +02:00
Felix 07d04280be
examples : clean up common code (#1871)
move some utility functions into common.h
2024-02-19 10:50:15 +02:00
dscripka a6fb6ab597
examples : added audio_ctx argument to main and server (#1857)
* added audio_ctx argument to main and server examples

* Better default value

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* better default value (again)

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-12 09:19:07 +02:00
Georgi Gerganov f273e66dc6
examples : initialize context params properly (#1852) 2024-02-11 16:39:12 +02:00
George Hindle f7908f9bb8
params : don't compute timestamps when not printing them (#1755) 2024-01-12 13:24:38 +02:00
Georgi Gerganov 29f78392c1
main : add cli option to disable system prints (#1740) 2024-01-08 16:41:28 +02:00
Felix eff3570f78
server : add a REST Whisper server example with OAI-like API (#1380)
* Add first draft of server

* Added json support and base funcs for server.cpp

* Add more user input via api-request

also some clean up

* Add reqest params and load post function

Also some general clean up

* Remove unused function

* Add readme

* Add exception handlers

* Update examples/server/server.cpp

* make : add server target

* Add magic curl syntax

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-11-20 21:40:24 +02:00
Georgi Gerganov b6c5f49b78
whisper : add batched decoding (#1486)
* whisper : add whisper_batch

* whisper : move kv_self to whisper_state

* whisper : full batched decoding support

* whisper : fix memory leak in whisper_batch

* whisper : fix mem leak again + remove oboslete function

* whisper : clear kv cache when using whisper_decode API

* whisper : speed-up sampling

* whisper : fix decoders initializer

* bench : add batch size 5 bench

* whisper : add comment about the KV cache size

* whisper : add check for max number of decoders

* whisper : avoid starting sampling threads with bs=1

* whisper : enable beam-search by default

* cuda : sync llama.cpp fixes
2023-11-15 16:12:52 +02:00
Jhen-Jie Hong 0463028bc2
whisper : add context param to disable gpu (#1293)
* whisper : check state->ctx_metal not null

* whisper : add whisper_context_params { use_gpu }

* whisper : new API with params & deprecate old API

* examples : use no-gpu param && whisper_init_from_file_with_params

* whisper.objc : enable metal & disable on simulator

* whisper.swiftui, metal : enable metal & support load default.metallib

* whisper.android : use new API

* bindings : use new API

* addon.node : fix build & test

* bindings : updata java binding

* bindings : add missing whisper_context_default_params_by_ref WHISPER_API for java

* metal : use SWIFTPM_MODULE_BUNDLE for GGML_SWIFT and reuse library load

* metal : move bundle var into block

* metal : use SWIFT_PACKAGE instead of GGML_SWIFT

* style : minor updates

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-11-06 11:04:24 +02:00
Aarni Koskela bce49a260e
examples : Implement JSON output for Token-Level data in main (#1358) 2023-10-31 19:54:52 +00:00
mkiol 940cdb1396
whisper : abort callback improvements (#1345)
* whisper : initialize abort_callback to null

* whisper : add example how to use abort_callback
2023-10-08 17:22:24 +03:00
Georgi Gerganov 2818de21ff
examples : fix build + compile warnings (close #1256) 2023-09-07 12:33:12 +03:00
bobqianic 7e54df414e
whisper : significantly improve the inference quality (#1148)
* Fix MSVC compile error C3688

Instead of simply using 'add_compile_options(/utf-8)' to address the MSVC compile error C3688, a better approach would be to handle it in a way that prevents passing '/utf-8' to NVCC.

* Significantly improve inference quality

In the function `log_mel_spectrogram_worker_thread`, there's an array out-of-bounds issue occurring during the calculation of complex number moduli. This issue is causing disruptions in the FFT spectrum, which, in turn, is reducing the quality of inference.

* Significantly improve inference quality

At last, I've pinpointed the actual source of the problem. Given that the frequency spectrum generated from real input data is symmetrical around the Nyquist frequency, there's a for-loop within the `log_mel_spectrogram_worker_thread` function that attempts to fold the frequency spectrum. Regrettably, a bug within this for-loop is causing a frame shift in the frequency spectrum. The previous attempt to remedy this, which involved using `fft_size + 1` when calculating the modulus, was merely a band-aid solution and did not address the underlying issue.

* Addressed a few minor issues

Fixed the issue of `fft_out` continuously expanding. Resolved the fallback caused by using 'break' instead of `fft_in[j] = 0`.

* Significantly improve inference quality 

Thanks for your patience everyone. It's finally sorted out. Now, the right side of the FFT spectrum is being flipped over to the left, and the amplitudes at corresponding positions on the left and right are added together (the spectrum on the left needs to be shifted by one position), then the average is calculated. FFT_OUT[0] is no longer discarded, making full use of the limited space to pack in more information.

* Add annotation and performance improvement

* Calculate FFT only when fft_in are not all zero

* Some minor performance improvement

* Fixed a bug impacting inference quality

* The first version after all the analysis is completed.

* Fix some bugs and add debug mode

* Fixed several bugs

* Temporarily disable speed-up mode and add debug mode.

* Add debug mode

* Disable speed-up mode and add debug mode

* Fix CI error (#1)

* Fix error

* Fix error

* Fixed several bugs including [BLANK_AUDIO] problem

* Remove Hard-coded hann window

* Some Final Fix (#2)

* Fix error

* Fix error

* Probably the last commit

* Probably the last commit

* whisper : minor coding style changes

* whisper : remove debug from public API

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-08-27 19:51:33 +03:00
Yunès 7ef3f3837e
main : log probs to text file (#1205)
* token/probability file generated with -ls

* code comment cleaning

* main : indentations

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-08-27 19:09:06 +03:00
Hrishikesh Barman 925915ae37
whisper : move progress calculation out of whisper.cpp (#1081)
Current `progress_step` was hardcoded into whisper.cpp, this resulted in
bindings having to access progress only at that step even if progress
callback was being called at every iteration.

With this change we get greater granularity progress reporting from
whisper.cpp and bindings/implementations can define their own progress step.
2023-07-25 18:53:34 +03:00
Georgi Gerganov 4774d2feb0
whisper : minor OpenVINO refactoring (#1037)
Hopefully I didn't break something - haven't tested
2023-07-04 20:28:27 +03:00
Ryan Metcalfe 62b81276e0
whisper : add OpenVINO support (#1037)
* openvino: use OpenVINO encoder inference

* openvino: add python script for OpenVINO model generation

* whisper: Fix 'unused' warnings when OpenVINO isn't enabled in build

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* whisper: Fix compilation error

* whisper: revert whisper_get_openvino_path_encoder & whisper_get_openvino_path_cache to non-const func signatures

* cmake: Add openvino-encoder as separate object target

* whisper : minor style fixes

* minor : indentation fixes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-04 15:56:11 +03:00
Akash Mahajan c8d0f5fe98
whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize (#1058)
* add HuggingFace mirror to download  ggml model

* support tdrz via simple hack overriding solm tokens

* fix incorrect translate/transcribe token_ids that are not static const

* add apollo 13 sample for tdrz demo

* render [SPEAKER TURN] consistently in all terminal output using vocab.id_to_token

* extend whisper_segment with speaker_turn_next field and save in json output

* fix failing go build

* slipped in some python syntax whoops

* whisper : finalize tinydiarize support (add flag + fixes)

* whisper : tdrz support for word-level timestamps (respect max_len)

* java : try to fix tests after adding tdrz_enable flag

* main : remove TODO leftover

* java : fix params order list after adding "tdrz_enable"

* whisper : fix solm and add nosp token

* main : print tinydiarize help

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-04 09:45:00 +03:00
Colin 14baf2e7f3
main : add diarization support for all current output types (#1031)
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-25 15:07:57 +03:00
Georgi Gerganov 5feb0dffba
ggml : sync latest ggml lib 2023-06-25 14:30:44 +03:00
faker 598f607e28
main : gracefully exit when invalid params are passed (#1002)
* Refactor whisper_params_parse to return false on failure

* Updated help flag behavior
2023-06-25 13:51:59 +03:00
Rich Jones d652cf12ec
main : fix help for --no-timestamps arg (#908) 2023-05-14 17:54:57 +03:00
CRD716 b806420873
whisper : add detect-language mode (#853)
* add detectlanguage flag

* renaming and help

* no idea why that last one didn't commit

* run language detection if dl is set

* help message fix

* various fixes

* fix quitting

* fix language being english on print
2023-05-02 19:51:52 +03:00
Georgi Gerganov 794b162a46
whisper : add integer quantization support (#540)
* whisper : add integer quantization support

* examples : add common-ggml + prepare to add "quantize" tool

* whisper : quantization tool ready

* whisper : fix F32 support

* whisper : try to fix shared lib linkage

* wasm : update quantized models to Q5

* bench.wasm : remove "medium" button

* bench.wasm : fix custom model button

* ggml : add Q5_0 and Q5_1 WASM SIMD

* wasm : add quantized models to all WASM examples

* wasm : bump DB version number to 2

* talk-llama : update example to latest llama.cpp

* node : increase test timeout to 10s

* readme : add information for model quantization

* wasm : add links to other examples
2023-04-30 18:51:57 +03:00
Laytan Laats 70567eff23
main : escape quotes in csv output (#815) 2023-04-23 19:01:59 +03:00
Tauseef Mohiuddin eecf2c3d41
main : update escape_double_quotes() function (#776)
Updated the escape_double_quotes() function such that the function now escapes both double quotes and backslashes in the input string.

Changes Made:

- Renamed the function to escape_quotes_and_backslashes

- Modified the condition in the first loop to increment the value of 'escaped_length' for both double quotes and backslashes.

- Modified the condition in second loop to add a backslash before the current character if it is a double quote or a backslash.

Resolves: #769
2023-04-23 16:47:30 +03:00
Georgi Gerganov f19e23fbd1
whisper : restore decoder temperature fallbacks
I disabled this because there were many complaints about slow decoding.
The current implementation does not allow batching the decoders when
using the "best of" or "beam size" parameters, so the decoding time is
proportional to the number of decoders, which is obviously not great.

However, now there are even more complaints about wrong decodings and
repetition.

So, making a compromise by re-enabling the fallbacks, but defaulting to
just 2 "best of" / "beam size" decoders. Also, the temperature step is
increased from 0.2 to 0.4 - i.e. from maximum of 5 fallbacks to maximum
of 2.

Also, the stream example now has fallbacks enabled by default.

close #471 #477 #508 #612 #719 #731
2023-04-15 16:12:55 +03:00
LittleLoli 66110dafcc
main : add lrc output support (#718)
* add lrc output support.

* fix wrong comment
2023-04-14 19:35:33 +03:00
Georgi Gerganov 514cd04452 whisper : fix bug in prompt processing (close #705)
Was dereferencing a dangling pointer
2023-04-14 19:17:07 +03:00
Georgi Gerganov a7f1f33715
main : add <cstring> header 2023-03-29 23:59:45 +03:00
Egor Egorov 0f759f125d
main : fix typo in JSON output (#648)
* typo in JSON output

* fix double quotes in JSON output
2023-03-29 23:26:39 +03:00
Jhen-Jie Hong eefed45e37
whisper : add initial_prompt param (#645) 2023-03-29 23:23:23 +03:00
Leo Moll 8fcd1a3b32
main : provide option for creating JSON output (#615)
* examples : provide option for exporting also as JSON file (ggerganov/whisper.cpp#614)

* main : remove leftovers

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-22 21:37:36 +02:00
venkr b597c5a779
qual-bench.sh : add quality comparison tool, and update main.cpp to allow using a font file (#569) 2023-03-06 19:18:11 +02:00
sandrohanea 59fdcd19c8
whisper : add whisper_state + default state on the whisper_context (#523)
* Added whisper state + default state on the whisper_context

* Fixed some examples and bindings

* Fixed whisper_n_len (which was used in some binding) and added whisper_n_len_from_state

* Fixed comments

* whisper : reuse kv_cache_free() and fix compiler warnings

* whisper : clean-up the API comments

---------

Co-authored-by: Sandro Hanea <sandrohanea@microsoft.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-05 21:42:19 +02:00
HY. Kelvin Lee 72af0f5697
main : add csv header (#552) 2023-03-02 18:32:16 +02:00
Georgi Gerganov f254e78737
yt-wsp.sh : print help on empty args 2023-02-18 09:42:31 +02:00
conradg 69e6e4644a
main : fix std in input (#503)
if we don't add this as an explicit check, then we get an "error: unknown argument: -" later on
2023-02-15 19:31:16 +02:00
Georgi Gerganov 09d7d2b68e
examples : refactor in order to reuse code and reduce duplication (#482)
* examples : refactor common code into a library

* examples : refactor common SDL code into a library

* make : update Makefile to use common libs

* common : fix MSVC M_PI ..

* addon.node : link common lib
2023-02-15 19:28:10 +02:00
Matija Pevec d012b5c7e4
whisper : add "split_on_word" flag when using using "max_len" option (#455)
* Update whisper.cpp

* fix: trim function

* feat: added flag to split on word

* fix: arguments for main
2023-02-05 14:44:23 +02:00
Georgi Gerganov 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
2023-02-04 09:45:52 +02:00
Alex Bacart 3b1960520a
main : CSV format export trimmed spaces fix (#444)
* Update main.cpp

Removed string trimming

* Update main.cpp

* Update main.cpp

* Revert "Update main.cpp"

This reverts commit d8924fdcfe.

* Revert "Update main.cpp"

This reverts commit 252e508d85.
2023-02-04 08:48:35 +02:00
Georgi Gerganov f583e2d2f5
main : we had accidentally disabled the temperature fallback .. (#291) 2023-01-18 22:51:41 +02:00
Chia-Hsiang Cheng 472a473fd1
main : add an option to accept optional output filenames (#424)
* Add an option to accept optional output filenames

* Format the file

Co-authored-by: Chia-Hsiang Cheng <gary.chiahsiang.cheng@gmail.com>
2023-01-18 21:26:31 +02:00
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
2023-01-15 11:29:57 +02:00