Commit Graph

235 Commits

Author SHA1 Message Date
Kirill 0026df4528
Merge a7a8169b99 into 1fe009caed 2026-08-15 10:18:37 +08:00
Daniel Bevenius 306c88f4d1
release : v1.9.2 (#3970) 2026-08-04 15:56:51 +02:00
Todd a630b35c6f
Adding ruby bindings change log (#3959) 2026-07-29 13:12:27 +09:00
KITAITI Makoto 97c56f1dc1
ruby : add VAD speech segments API (#3931)
* Bump version

* Add test for VAD segments API

* Implement VAD segments API

* Add signatures of VAD segments API

* Stop to dependent on mutex_m

* Check segment range for vad_segment_t0/t1

* Remove needless check

* Remove dead codes

* Fix index check for VAD segments

* Remove needless line

* Use NUM2DBL instead of RFLOAT_VALUE for safety

* Fix document

* Check type of samples

* Arrange CMake cache notation for older version

* Remove unnecessary line break

* Check return value of whisper_vad_segments_from_samples

* Fix type of VAD::Segment#start_time and #end_time

* Prevent dangling pointer from Params to VAD::Params

* Fix typos

* Update README

* Make test follow fix of impl

* Use segments_from_samples_body in ruby_whisper_vad_detect

* Run segments_from_samples without GVL

* Remove unnecessary codes

* [skip ci]Remove trailing whitespace

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2026-07-28 15:08:44 +09:00
Daniel Bevenius f049fff95a
release : v1.9.1 (#3892) 2026-06-19 06:12:37 +02:00
Daniel Bevenius 86c40c3bd6
release : v1.9.0 (#3886) 2026-06-17 11:36:57 +02:00
KITAITI Makoto 0d14756929
ruby : add support for Parakeet (#3885)
* Add Whisper::Parakeet::Params

* Add tests for Parakeet::Params

* Remove unused variabel

* Add callbacks to Parakeet::Params

* Group callback and user_data params

* Undefine local macros

* Define GetParakeetParams

* Remove unused variable

* Use ITERATE_CALLBACK_PARAMS

* Use ITERATE_CALLBACK_PARAMS instead of ITERATE_USER_DATA_PARAMS

* Fix memsize

* Remove unnecessary macros

* Simplify params registration

* Define Parakeet

* Add hook methods to Parakeet::Params

* Fix typo

* Check callback container in GetParakeetParams

* Reduce if

* Free parakeet_full_params

* Implement Parakeet::Context#initialize

* Add TestParakeetContext

* Add Parakeet::Segment

* Prevent double-free

* Add Parakeet::Context#transcribe

* Add Parakeet::Context#each_segment

* Define Parakeet::Segment attributes

* Define Parakeet::Segment#deconstruct_keys

* Add tests for Parakeet::Segment#deconstruct_keys

* Run Parakeet::Context#transcribe without GVL

* Make it to abort for Parakeet

* Add Parakeet.log_set

* Define Parakeet::Token

* Define Parakeet::Segment#each_token

* Implement some hooks of Parakeet::Params

* Convert int to VALUE

* Implement hooks for Parakeet

* Implement Parakeet::Context#full

* Add tests for Parakeet::Context#full

* Add Parakeet to RBS

* Fix ruby_whisper_parakeet_params_free

* Free ruby_whisper_parakeet_context

* Add tests for hooks

* Add Parakeet section to README

* Add more attributes of Parakeet::Context

* Add tests for Parakeet::Context's attributes

* Update RBS

* Register parakeet-tdt-0.6b-v3

* Narrow scope of log constants

* Extract activate and deactivate of log_queue

* Make start_log_callback_thread private

* Don't call start_log_callback_thread unncecessarilly

* Early return from log_queue_enqueue when not active

* Gropu log_queue members

* is_active -> is_open

* Fix English

* Share parakeet full body function

* ruby_whisper_parakeet_abort_callback_user_data -> ruby_whisper_abort_callback_user_data

* NULL check for callback containers

* Fix Parakeet.log_set

* Omit Parakeet tests on CI

* Extract Whisper::LogSettable

* Join log callback thread in a log queue function

* Revert Join log callback thread in a log queue function

* Extract output methods to modules

* Move Parakeet init functions into init_parakeet()

* Add output methods to Parakeet classes

* Add Parakeet's output methods to RBS

* Use Whisper::Output in RBS

* Add LogSettable to RBS

* Fix module Token -> class Token

* Add Parakeet::Model

* Add test for Parakeet::Model

* Add Parakeet::Model to RBS

* Move position of Parakeet::Model in RBS

* Parakeet -> TestBase::Parakeet

* Add Parakeet::Context#model in RBS

* Add Whisper::Output

* Fix nil check

* Define ruby_whisper_parakeet_model_memsize

* Fix order of declaration in ruby_whisper_parakeet_model_get_xxx

* Define Parakeet.system_info_str

* Add test for Parakeet.system_info_str

* Add signature of Parakeet.system_info_str

* Define Parakeet::VERSION

* Add test for Parakeet::VERSION

* Add signature of Parakeet::VERSION

* Add Parakeet::Context::Params

* Make Parakeet::Context.new accept Context::Params

* Add test for Parakeet::Context.new with Context::Params

* Update RBS

* Remove params from Parakeet::Params which are moved from whisper_parakeet_full_params

* Remove tests for removed params

* Make Parakeet tests follow original behavior changes

* Add Parakeet model shortcuts

* Alloc token data in factory instead of alloc func

* Fix variable name

* Update RBS

* Refactor log settable module

* Use log settable for Whisper

* Address deadlock

* Make test follow change of log queue implementation

* Refactor to make abort callback use the same way to parakeet's way

* Remove redundant structs

* Fix test name

* Fix README

* Add missing parallel transcription

* Fix test for parakeet info

* Remove removed params

* Wait for logs dequeued

* Fix instance variable name

* Load etc feature

* Remove unnecessary comment

* Remove unnecessary thread safety check

* Remove outdated comment

* Skip downloading model if cache exists

* Change Hugging Face URI for Parakeet models

* Bump required Ruby version to 3.3

* Fix English
2026-06-17 06:42:09 +02:00
Daniel Bevenius 9efddafb91
parakeet : add support for NVIDIA Parakeet (#3735)
* parakeet : add support for NVIDIA Parakeet


Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-06-16 20:44:10 +02:00
Daniel Bevenius 48f628a848
release : v1.8.7 (#3881) 2026-06-16 12:28:23 +02:00
Georgi Gerganov 23ee03506a
release : v1.8.6 2026-06-01 14:56:20 +03:00
Georgi Gerganov e0fd1f6787
release : v1.8.5 2026-05-25 13:06:33 +03:00
OrbisAI Security b3877e10c0
fix: in bindings/ruby/test/jfk_reader/jfk_reader in jfk_reader.c (#3756)
* fix: V-002 security vulnerability

Automated security fix generated by Orbis Security AI

* fix(ruby): use Ruby allocator macros in jfk_reader and fix memory leak

- Replace calloc/free with ALLOC_N/xfree to match Ruby binding conventions
  (ALLOC_N handles overflow checking and raises NoMemoryError on failure)
- Free temporary samples buffer after conversion loop (was leaked)
- Add NULL check for fopen return value with rb_raise
- Add comment clarifying n_samples is a compile-time constant

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(ruby): return false instead of rb_raise in memory_view callback

rb_memory_view_get_func_t callbacks should communicate errors via
return value (false), not exceptions. rb_memory_view_get has no
exception-handling wrapper around get_func calls.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* replacing ALLOC_N with rb_protect as ALLOC_N raises Ruby exceptions

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-05-25 08:19:23 +02:00
annaeina f08258abd7
whisper : fix max_tokens skipping remaining audio (#3798)
* whisper: fix max_tokens skipping remaining audio

* add PR reference comment as suggested

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

* fix(ci): enable artifact overwrite
2026-05-13 07:32:00 +02:00
KITAITI Makoto c81b2dabbc
ruby : transcribe without GVL, accept more MemoryViews, Windows support, fix memory size report, improve document (#3775)
* Change MemoryView example using NDAV

* Add note on audio attributes for #full and #full_parallel

* Support more variants of MemoryView

* Use IO.popen instead of Kernel.` for Windows compatibility

* Use cmake's -C option instead of multiple -D options

* Fix memsize calculation

* Remove unused argument

* Add is_interrupted field to abort callback container

* Fix RBS syntax

* Address document comment for RDoc

* Add .document for RDoc

* Add .rdoc_options

* Run #full without GVL

* Initialize callbacks with nil

* Specify implicity Whisper::Params to distinguish from Whisper::Context::Params

* Run callbacks without GVL

* Call log callback with GVL

* Run full_parallel without GVL

* Run transcribe without GVL

* Fix ruby_whisper_lock_gvl and ruby_whisper_unlock_gvl

* Fix return value of encoder_begin_callback

* Report GVL unlocking from transcribe

* Remove unused interface

* Restore overload of full_parallel

* Close process

* Fix struct name

* Make is_without_gvl thread local

* Use rb_thread_call_with_gvl instead of global variable

* Retrieve instance variable in GVL

* Narrow acceptable MemoryView format

* Fix option cache path

* Reduce files in package

* Use append_cflags

* Add ext/*.rb to task dependencies

* Use copy instead of cp

* Make TestPackage more portable

* Patch for lower version Ruby

* Make build scripts more portable

* Add Windows support

* Don't raise exceptions
2026-05-07 06:28:18 +02:00
KITAITI Makoto 76684141a5
ruby : fix dangling pointers, memory leak, and SEGV on parallel transcription (#3715)
* Prevent dangling pointers

* Use proper free function

* Free callback containers

* Set default log callback when nil is passed to log_set

* Raise error if callbacks set when parallel transcription

* Bump version to 1.3.7

* Make tests follow spec change

* Add note on parallel transcription and callbacks

* Update signature of Whisper.log_set [skip ci]
2026-03-22 02:03:00 +09:00
Georgi Gerganov 9386f23940
release : v1.8.4 2026-03-19 10:40:13 +02:00
Alan 79218f51d0
go : handle EOF correctly in model download (#3671) 2026-03-16 13:44:18 +02:00
KITAITI Makoto 30c5194c96
ruby : null-check (#3689)
* Introduce null-check to prevent SEGV

* Fix error message
2026-03-05 14:36:42 +09:00
KITAITI Makoto 941bdabbe4
ruby : add `Whisper::Context::Params`, fix token memory management (#3647)
* Don't convert to temporary VALUE

* Define Whisper::Context::Params

* Add test for Whisper::Context::Params

* Implement Whisper::Context::Params

* Add tests for Context::Params

* Fix Whisper::Token memory management

* Add test for token_timestamps

* Make Context accept Context::Params

* Make Context::Params.new accept keyword args

* Add test for Context::Params.new with keyword args

* Add signature of Context::Params

* Add example for Whisper::Token

* Fix typos

* Revert "Don't convert to temporary VALUE"

This reverts commit dee66e7384.

* Hold Token#text as Ruby objectd

* Don't use pointer for ruby_whisper_context_params.params

* Use RUBY_DEFAULT_FREE instead of custom function

* Update bindings/ruby/README.md

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* Add document for Whisper::Context::Params

---------

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2026-02-04 20:33:09 +09:00
KITAITI Makoto aa1bc0d1a6
ruby : add `VAD::Context#segments_from_samples`, allow Pathname, etc. (#3633)
* ruby : Bump version to 1.3.6

* Fix code in example

* Add sample code to transcribe from MemoryView

* Define GetVADContext macro

* Use GetVADContext

* Extract parse_full_args function

* Use parse_full_args in ruby_whisper_full_parallel

* Free samples after use

* Check return value of parse_full_args()

* Define GetVADParams macro

* Add VAD::Context#segments_from_samples

* Add tests for VAD::Context#segments_from_samples

* Add signature for VAD::Context#segments_from_samples

* Add sample code for VAD::Context#segments_from_samples

* Add test for Whisper::Context#transcribe with Pathname

* Make Whisper::Context#transcribe and Whisper::VAD::Context#detect accept Pathname

* Update signature of Whisper::Context#transcribe

* Fix variable name

* Don't free memory view

* Make parse_full_args return struct

* Fallback when failed to get MemoryView

* Add num of samples when too long

* Check members of MemoryView

* Fix a typo

* Remove unnecessary include

* Fix a typo

* Fix a typo

* Care the case of MemoryView doesn't fit spec

* Add TODO comment

* Add optimazation option to compiler flags

* Use ALLOC_N instead of malloc

* Add description to sample code

* Rename and change args: parse_full_args -> parse_samples

* Free samples when exception raised

* Assign type check result to a variable

* Define wrapper function of whisper_full

* Change signature of parse_samples for rb_ensure

* Ensure release MemoryView

* Extract fill_samples function

* Free samples memory when filling it failed

* Free samples memory when transcription failed

* Prepare transcription in wrapper funciton

* Change function name

* Simplify function boundary
2026-01-30 22:59:36 +09:00
ciricc a7a8169b99 feat: sync with upstream 2026-01-21 03:44:02 +03:00
ciricc 3d5d94412c merge: sync with upstream 2026-01-21 03:07:46 +03:00
Georgi Gerganov 2eeeba56e9
release : v1.8.3 2026-01-15 11:54:31 +02:00
KITAITI Makoto 679bdb53db
ruby : fix segmentation fault (#3591)
* Mark long live variable

* Fix test for Whisper::Token#deconstruct_keys(nil)

* Don't use long live variable

* Fix indentation
2026-01-05 17:41:22 +09:00
KITAITI Makoto 6114e69213
ruby : add Whisper::Token, fix model URI (#3575)
* Define and use macro to get context safely

* Add test to check SEGV

* Move installation guid after usage

* [skip ci]Change doc slightly

* [skip ci]Fix a typo in README

* [skip ci]Add carry_initial_prompt option in README

* Define GetVADSegments and use it

* Use GetContext

* Fix download URI of small.en-tdrz

* Fix URI of CoreML models corresponding to quantized models

* Cache computed string

* Remove unused argument

* Add Whisper::Token

* Add document comments

* Rename function: rb_whisper_token_s_new -> ruby_whisper_token_s_init

* Fix size of token

* Insert _get into function names

* Add Whisper::Token#text

* Add test for Whisper::Token#text

* Declare static if possible

* Change method names

* Add Whisper::Token#deconstruct_keys

* Add tests for Whisper::Token#deconstruct_keys

* Add signatures for Whisper::Token

* Complete signature

* [skip ci]Add n_tokens to document of Segment
2025-12-24 16:52:16 +09:00
Josh Montoya 9f5ed26e43
go : Enable VAD for Go bindings (#3563)
* reset context.n so that NextSegment can be called for multiple Process calls

* enable VAD params
2025-12-10 13:31:36 +02:00
Josh Montoya a8f45ab11d
go : reset context.n in Process() (#3503) 2025-12-08 18:33:07 +02:00
KITAITI Makoto 27f485a14c
vad : Silero VAD v6.2.0 (#3524)
* Add ggml-silero-v6.2.0 to download candidates

* Make default VAD model ggml-silero-v6.2.0

* Make VAD model in documentations ggml-silero-v6.2.0
2025-11-17 22:26:17 +09:00
KITAITI Makoto d9b7613b34
ruby : VAD separately from ASR (#3518)
* Add Whisper::VAD::Context

* Add test for Whisper::VAD::Context

* Add Whisper::VAD::Segment

* Add Whisper::VAD::Segments

* Add Whisper::VAD::Context#detect

* Define Whisper::VAD::Segments#each

* Define Whisper::VAD::Segment#start_time and #end_time

* Define Whisper::VAD::Segment#deconstruct_keys

* Add tests for Whisper::VAD family

* Add signatures for VAD family

* Add document on VAD in README

* Define Whisper::VAD::Segments#length

* Add test for Whisper::VAD::Segments#length

* Add signature of Segments#length

* Make vad_segments responsible to initialize VAD::Segments

* Remove meaningless argument check

* Check NULL of segments member

* Add tests for Whisper::VAD::Segments

* Initialize Whisper::VAD::Segment on .allocate

* Add tests for Whisper::VAD::Segment

* Check NULL of context member

* Add test for Whisper::VAD::Context.allocate
2025-11-13 10:15:26 +09:00
KITAITI Makoto c62adfbd1e
ruby : tiny bug fix (#3490)
* Remove build-xcframework.sh from package

* Remove unused variable

* Bump version to 1.3.5

* Don't use variable before declaration
2025-10-29 03:50:44 +09:00
Georgi Gerganov 4979e04f5d
release : v1.8.2 2025-10-15 10:29:42 +03:00
Georgi Gerganov a91dd3be72
release : v1.8.1 2025-10-12 11:17:59 +03:00
Andreas Lubbe 85871a9469
whisper : add support for --carry-initial-prompt (#3395)
* Add support for --carry-initial-prompt

* PR fixes for ruby and go

* Refactoring for readability

* WIP 1

* WIP 2

* PR fixes

* More PR fixes

* PR fix

* Further simplification

* d'oh

* One more logic fix

* Update src/whisper.cpp

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

* Truncate prompt_past0 upon initialization

* Slight simplification

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-10-10 19:51:15 +03:00
KITAITI Makoto 8877dfc11a
[skip ci]Bump Ruby bindings' version to 1.3.4 (#3461) 2025-10-08 20:45:20 +09:00
KITAITI Makoto 7849aff7a2
ruby : Loose RegExp for test (#3448) 2025-10-01 15:33:11 +03:00
Daniel Bevenius 2a56869669
bindings-java : disable flash attention by default (#3445)
This commit disables flash-attention for the Java binding test so that
the testFullTranscribe test passes.

Without this change the test was failing because the expected output
mismatches after the flash-attention change:
```console
<And so my fellow Americans ask not what your country can do for you ask what you can do for your country.>
but was:
<and so my fellow Americans ask not what your country can do for you ask what you can do for your country>
```

An alternative would also be to update the expected output but it felt
better to keep the same expected output and disable flash-attention and
not just change the expected output to match the new behavior.
2025-10-01 09:13:34 +02:00
Georgi Gerganov 41fc9dea6a
release : v1.8.0 2025-09-30 21:25:36 +03:00
ciricc 5711a71d0f fix: fix sampling type 2025-09-20 20:23:19 +03:00
ciricc 91f5cc12f7 refactor: added segment formatiing, fixed benchmark printings 2025-09-20 17:03:25 +03:00
ciricc 50caee3467 doc: benchmark step by step doc 2025-09-20 16:31:45 +03:00
ciricc bf72a5b7e2 doc: added README for how-to with the new contexts, removed SetGate public method 2025-09-20 16:15:28 +03:00
ciricc 2305a6142a feat: split context into stateful/stateless; add concurrency gate, added model context params, benchmarks, silence mode for the ggml 2025-09-20 15:56:48 +03:00
ciricc 8f9ad60fca refactor(go bindings): make ModelContext and StatefulContext public 2025-09-14 04:39:26 +03:00
ciricc 125ea6122b refactor(go bindings): remove new methods from the Model interface 2025-09-14 02:59:42 +03:00
ciricc f943c8f1d4 refactor(go bindings): remove public Model() method 2025-09-14 02:53:13 +03:00
ciricc 99722972d6 refactor(go bindings): remove public Parameters from context 2025-09-14 02:47:51 +03:00
ciricc b751ec1f55 fix(go bindings): unit tests and exported interfaces 2025-09-14 02:41:28 +03:00
ciricc 221e93a5d7 refactor(go bindings): fix backward compatibility for the interfaces 2025-09-14 02:31:10 +03:00
ciricc ba990ab0a8 refactor(go bindings): fix backward compatibility for error andling logic 2025-09-14 02:04:06 +03:00
ciricc 01f5c6b708 refactor(go bindings): remove public method accessing unsafe whisper 2025-09-14 01:47:57 +03:00