whispercpp 1.3.4 → 1.3.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d790b742ddf3f6071ba7cc41ea9a16d2daa1363d4fee9c984ad2609fb19ed9fc
-  data.tar.gz: 97b213ff5bc5cee1a2880d0e69d4ba9b89da309f003957a66f89ea7bdbfa1ee7
+  metadata.gz: 90c3f74c4f4c20ba9f9276f16fad4efa3458cab361f1dcdceb9ef436a3845ddc
+  data.tar.gz: 9001366168e697842700adc27305e0771c97e5ba3533c567c3cc6363004b2332
 SHA512:
-  metadata.gz: e1ea6c6082532e90b26e17041bd0649f91e32fc70cb489bff0c9d83e4d92431e8d36a54d47904070f1d799e9df9d2fe7dc5f4cc668bf84c6339b7edf4c2b4d45
-  data.tar.gz: e2007190f93a5f6cb21d8014e07c650aa0e835286eb13131d268d02e563c519c23e1ccce60c90f7da5f921fb4ed1eaec143239627015fb6c40e02188e5eaf34c
+  metadata.gz: d57baa8f961809c0323c83df79b5373cc2aefa38b5d21e3c538fea07ac6e74b95cfa86565bd64fd35ee385afb8baee32d9cb445fa07b7c51d4556ffcb0a0bda5
+  data.tar.gz: 6f1418ae638dc69fbff3d2accbb7652a360f6d21d34d003df7953054773bd7056add1051a302deb59649a6674c89fb22a419809ba09f166458f4da396945dd5f

data/README.md

@@ -5,43 +5,6 @@ whispercpp
 
 Ruby bindings for [whisper.cpp][], an interface of automatic speech recognition model.
 
-Installation
-------------
-
-Install the gem and add to the application's Gemfile by executing:
-
-    $ bundle add whispercpp
-
-If bundler is not being used to manage dependencies, install the gem by executing:
-
-    $ gem install whispercpp
-
-You can pass build options for whisper.cpp, for instance:
-
-    $ bundle config build.whispercpp --enable-ggml-cuda
-
-or,
-
-    $ gem install whispercpp -- --enable-ggml-cuda
-
-See whisper.cpp's [README](https://github.com/ggml-org/whisper.cpp/blob/master/README.md) for available options. You need convert options present the README to Ruby-style options, for example:
-
-Boolean options:
-
-* `-DGGML_BLAS=1` -> `--enable-ggml-blas`
-* `-DWHISER_COREML=OFF` -> `--disable-whisper-coreml`
-
-Argument options:
-
-* `-DGGML_CUDA_COMPRESSION_MODE=size` -> `--ggml-cuda-compression-mode=size`
-
-Combination:
-
-* `-DGGML_CUDA=1 -DCMAKE_CUDA_ARCHITECTURES="86"` -> `--enable-ggml-cuda --cmake_cuda-architectures="86"`
-
-For boolean options like `GGML_CUDA`, the README says `-DGGML_CUDA=1`. You need strip `-D`, prepend `--enable-` for `1` or `ON` (`--disable-` for `0` or `OFF`) and make it kebab-case: `--enable-ggml-cuda`.  
-For options which require arguments like `CMAKE_CUDA_ARCHITECTURES`, the README says `-DCMAKE_CUDA_ARCHITECTURES="86"`. You need strip `-D`, prepend `--`, make it kebab-case, append `=` and append argument: `--cmake-cuda-architectures="86"`.
-
 Usage
 -----
 
@@ -57,7 +20,8 @@ params = Whisper::Params.new(
   max_text_tokens: 300,
   translate: true,
   print_timestamps: false,
-  initial_prompt: "Initial prompt here."
+  initial_prompt: "Initial prompt here.",
+  carry_initial_prompt: true
 )
 
 whisper.transcribe("path/to/audio.wav", params) do |whole_text|
@@ -118,7 +82,8 @@ Or, you can download model files:
 ```ruby
 whisper = Whisper::Context.new("https://example.net/uri/of/your/model.bin")
 # Or
-whisper = Whisper::Context.new(URI("https://example.net/uri/of/your/model.bin"))
+uri = URI("https://example.net/uri/of/your/model.bin")
+whisper = Whisper::Context.new(uri)
 ```
 
 See [models][] page for details.
@@ -134,20 +99,20 @@ Support for Voice Activity Detection (VAD) can be enabled by setting `Whisper::P
 ```ruby
 Whisper::Params.new(
   vad: true,
-  vad_model_path: "silero-v5.1.2",
+  vad_model_path: "silero-v6.2.0",
   # other arguments...
 )
 ```
 
-When you pass the model name (`"silero-v5.1.2"`) or URI (`https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v5.1.2.bin`), it will be downloaded automatically.
-Currently, "silero-v5.1.2" is registered as pre-converted model like ASR models. You also specify file path or URI of model.
+When you pass the model name (`"silero-v6.2.0"`) or URI (`https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v6.2.0.bin`), it will be downloaded automatically.
+Currently, "silero-v6.2.0" is registered as pre-converted model like ASR models. You also specify file path or URI of model.
 
 If you need configure VAD behavior, pass params for that:
 
 ```ruby
 Whisper::Params.new(
   vad: true,
-  vad_model_path: "silero-v5.1.2",
+  vad_model_path: "silero-v6.2.0",
   vad_params: Whisper::VAD::Params.new(
     threshold: 1.0, # defaults to 0.5
     min_speech_duration_ms: 500, # defaults to 250
@@ -187,6 +152,42 @@ WEBVTT
 
 You may call `#to_srt`, too
 
+Installation
+------------
+
+Install the gem and add to the application's Gemfile by executing:
+
+    $ bundle add whispercpp
+
+If bundler is not being used to manage dependencies, install the gem by executing:
+
+    $ gem install whispercpp
+
+You can pass build options for whisper.cpp, for instance:
+
+    $ bundle config build.whispercpp --enable-ggml-cuda
+
+or,
+
+    $ gem install whispercpp -- --enable-ggml-cuda
+
+See whisper.cpp's [README](https://github.com/ggml-org/whisper.cpp/blob/master/README.md) for available options. You need convert options present in the README to Ruby-style options, for example:
+
+Boolean options:
+
+* `-DGGML_BLAS=1` -> `--enable-ggml-blas`
+* `-DWHISER_COREML=OFF` -> `--disable-whisper-coreml`
+
+Argument options:
+
+* `-DGGML_CUDA_COMPRESSION_MODE=size` -> `--ggml-cuda-compression-mode=size`
+
+Combination:
+
+* `-DGGML_CUDA=1 -DCMAKE_CUDA_ARCHITECTURES="86"` -> `--enable-ggml-cuda --cmake_cuda-architectures="86"`
+
+For boolean options like `GGML_CUDA`, the README says `-DGGML_CUDA=1`. You need strip `-D`, prepend `--enable-` for `1` or `ON` (`--disable-` for `0` or `OFF`) and make it kebab-case: `--enable-ggml-cuda`.  
+For options which require arguments like `CMAKE_CUDA_ARCHITECTURES`, the README says `-DCMAKE_CUDA_ARCHITECTURES="86"`. You need strip `-D`, prepend `--`, make it kebab-case, append `=` and append argument: `--cmake-cuda-architectures="86"`.
 
 API
 ---
@@ -324,6 +325,22 @@ whisper
 
 The second argument `samples` may be an array, an object with `length` and `each` method, or a MemoryView. If you can prepare audio data as C array and export it as a MemoryView, whispercpp accepts and works with it with zero copy.
 
+Using VAD separately from ASR
+-----------------------------
+
+VAD feature itself is useful. You can use it separately from ASR:
+
+```ruby
+vad = Whisper::VAD::Context.new("silero-v6.2.0")
+vad
+  .detect("path/to/audio.wav", Whisper::VAD::Params.new)
+  .each_with_index do |segment, index|
+    segment => {start_time: st, end_time: ed} # `Segment` responds to `#deconstruct_keys`
+
+    puts "[%{nth}: %{st} --> %{ed}]" % {nth: index + 1, st:, ed:}
+  end
+```
+
 Development
 -----------
 

data/ext/extconf.rb

@@ -3,9 +3,9 @@ require_relative "options"
 require_relative "dependencies"
 
 cmake = find_executable("cmake") || abort
-options = Options.new(cmake)
+options = Options.new(cmake).to_s
 have_library("gomp") rescue nil
-libs = Dependencies.new(cmake, options)
+libs = Dependencies.new(cmake, options).to_s
 
 $INCFLAGS << " -Isources/include -Isources/ggml/include -Isources/examples"
 $LOCAL_LIBS << " #{libs}"

data/ext/ruby_whisper.c

@@ -6,10 +6,14 @@ VALUE mWhisper;
 VALUE mVAD;
 VALUE cContext;
 VALUE cParams;
+VALUE cVADContext;
 VALUE cVADParams;
+VALUE cVADSegments;
+VALUE cVADSegment;
 VALUE eError;
 
 VALUE cSegment;
+VALUE cToken;
 VALUE cModel;
 
 ID id_to_s;
@@ -34,9 +38,13 @@ extern VALUE ruby_whisper_segment_allocate(VALUE klass);
 extern void init_ruby_whisper_context(VALUE *mWhisper);
 extern void init_ruby_whisper_params(VALUE *mWhisper);
 extern void init_ruby_whisper_error(VALUE *mWhisper);
-extern void init_ruby_whisper_segment(VALUE *mWhisper, VALUE *cSegment);
+extern void init_ruby_whisper_segment(VALUE *mWhisper);
+extern void init_ruby_whisper_token(VALUE *mWhisper);
 extern void init_ruby_whisper_model(VALUE *mWhisper);
 extern void init_ruby_whisper_vad_params(VALUE *mVAD);
+extern void init_ruby_whisper_vad_context(VALUE *mVAD);
+extern void init_ruby_whisper_vad_segment(VALUE *mVAD);
+extern void init_ruby_whisper_vad_segments(VALUE *mVAD);
 extern void register_callbacks(ruby_whisper_params *rwp, VALUE *context);
 
 /*
@@ -167,9 +175,13 @@ void Init_whisper() {
   init_ruby_whisper_context(&mWhisper);
   init_ruby_whisper_params(&mWhisper);
   init_ruby_whisper_error(&mWhisper);
-  init_ruby_whisper_segment(&mWhisper, &cContext);
+  init_ruby_whisper_segment(&mWhisper);
+  init_ruby_whisper_token(&mWhisper);
   init_ruby_whisper_model(&mWhisper);
   init_ruby_whisper_vad_params(&mVAD);
+  init_ruby_whisper_vad_segment(&mVAD);
+  init_ruby_whisper_vad_segments(&mVAD);
+  init_ruby_whisper_vad_context(&mVAD);
 
   rb_require("whisper/context");
   rb_require("whisper/segment");

data/ext/ruby_whisper.h

@@ -33,8 +33,47 @@ typedef struct {
   int index;
 } ruby_whisper_segment;
 
+typedef struct {
+  whisper_token_data *token_data;
+  const char *text;
+} ruby_whisper_token;
+
 typedef struct {
   VALUE context;
 } ruby_whisper_model;
 
+typedef struct {
+  struct whisper_vad_segments *segments;
+} ruby_whisper_vad_segments;
+
+typedef struct {
+  VALUE segments;
+  int index;
+} ruby_whisper_vad_segment;
+
+typedef struct {
+  struct whisper_vad_context *context;
+} ruby_whisper_vad_context;
+
+#define GetContext(obj, rw) do { \
+  TypedData_Get_Struct((obj), ruby_whisper, &ruby_whisper_type, (rw)); \
+  if ((rw)->context == NULL) { \
+    rb_raise(rb_eRuntimeError, "Not initialized"); \
+  } \
+} while (0)
+
+#define GetToken(obj, rwt) do {                                             \
+  TypedData_Get_Struct((obj), ruby_whisper_token, &ruby_whisper_token_type, (rwt)); \
+  if ((rwt)->token_data == NULL) { \
+    rb_raise(rb_eRuntimeError, "Not initialized"); \
+  } \
+} while (0)
+
+#define GetVADSegments(obj, rwvss) do { \
+  TypedData_Get_Struct((obj), ruby_whisper_vad_segments, &ruby_whisper_vad_segments_type, (rwvss)); \
+  if ((rwvss)->segments == NULL) { \
+    rb_raise(rb_eRuntimeError, "Not initialized"); \
+  } \
+} while (0)
+
 #endif

data/ext/ruby_whisper_context.c

@@ -147,7 +147,7 @@ ruby_whisper_initialize(int argc, VALUE *argv, VALUE self)
 VALUE ruby_whisper_model_n_vocab(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_vocab(rw->context));
 }
 
@@ -158,7 +158,7 @@ VALUE ruby_whisper_model_n_vocab(VALUE self)
 VALUE ruby_whisper_model_n_audio_ctx(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_audio_ctx(rw->context));
 }
 
@@ -169,7 +169,7 @@ VALUE ruby_whisper_model_n_audio_ctx(VALUE self)
 VALUE ruby_whisper_model_n_audio_state(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_audio_state(rw->context));
 }
 
@@ -180,7 +180,7 @@ VALUE ruby_whisper_model_n_audio_state(VALUE self)
 VALUE ruby_whisper_model_n_audio_head(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_audio_head(rw->context));
 }
 
@@ -191,7 +191,7 @@ VALUE ruby_whisper_model_n_audio_head(VALUE self)
 VALUE ruby_whisper_model_n_audio_layer(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_audio_layer(rw->context));
 }
 
@@ -202,7 +202,7 @@ VALUE ruby_whisper_model_n_audio_layer(VALUE self)
 VALUE ruby_whisper_model_n_text_ctx(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_text_ctx(rw->context));
 }
 
@@ -213,7 +213,7 @@ VALUE ruby_whisper_model_n_text_ctx(VALUE self)
 VALUE ruby_whisper_model_n_text_state(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_text_state(rw->context));
 }
 
@@ -224,7 +224,7 @@ VALUE ruby_whisper_model_n_text_state(VALUE self)
 VALUE ruby_whisper_model_n_text_head(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_text_head(rw->context));
 }
 
@@ -235,7 +235,7 @@ VALUE ruby_whisper_model_n_text_head(VALUE self)
 VALUE ruby_whisper_model_n_text_layer(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_text_layer(rw->context));
 }
 
@@ -246,7 +246,7 @@ VALUE ruby_whisper_model_n_text_layer(VALUE self)
 VALUE ruby_whisper_model_n_mels(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_n_mels(rw->context));
 }
 
@@ -257,7 +257,7 @@ VALUE ruby_whisper_model_n_mels(VALUE self)
 VALUE ruby_whisper_model_ftype(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_model_ftype(rw->context));
 }
 
@@ -268,7 +268,7 @@ VALUE ruby_whisper_model_ftype(VALUE self)
 VALUE ruby_whisper_model_type(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return rb_str_new2(whisper_model_type_readable(rw->context));
 }
 
@@ -291,7 +291,7 @@ VALUE ruby_whisper_full(int argc, VALUE *argv, VALUE self)
 
   ruby_whisper *rw;
   ruby_whisper_params *rwp;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   VALUE params = argv[0];
   TypedData_Get_Struct(params, ruby_whisper_params, &ruby_whisper_params_type, rwp);
   VALUE samples = argv[1];
@@ -377,7 +377,7 @@ ruby_whisper_full_parallel(int argc, VALUE *argv,VALUE self)
 
   ruby_whisper *rw;
   ruby_whisper_params *rwp;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   VALUE params = argv[0];
   TypedData_Get_Struct(params, ruby_whisper_params, &ruby_whisper_params_type, rwp);
   VALUE samples = argv[1];
@@ -463,7 +463,7 @@ static VALUE
 ruby_whisper_full_n_segments(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_full_n_segments(rw->context));
 }
 
@@ -477,7 +477,7 @@ static VALUE
 ruby_whisper_full_lang_id(VALUE self)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   return INT2NUM(whisper_full_lang_id(rw->context));
 }
 
@@ -502,7 +502,7 @@ static VALUE
 ruby_whisper_full_get_segment_t0(VALUE self, VALUE i_segment)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   const int c_i_segment = ruby_whisper_full_check_segment_index(rw, i_segment);
   const int64_t t0 = whisper_full_get_segment_t0(rw->context, c_i_segment);
   return LONG2NUM(t0);
@@ -520,7 +520,7 @@ static VALUE
 ruby_whisper_full_get_segment_t1(VALUE self, VALUE i_segment)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   const int c_i_segment = ruby_whisper_full_check_segment_index(rw, i_segment);
   const int64_t t1 = whisper_full_get_segment_t1(rw->context, c_i_segment);
   return LONG2NUM(t1);
@@ -538,7 +538,7 @@ static VALUE
 ruby_whisper_full_get_segment_speaker_turn_next(VALUE self, VALUE i_segment)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   const int c_i_segment = ruby_whisper_full_check_segment_index(rw, i_segment);
   const bool speaker_turn_next = whisper_full_get_segment_speaker_turn_next(rw->context, c_i_segment);
   return speaker_turn_next ? Qtrue : Qfalse;
@@ -556,7 +556,7 @@ static VALUE
 ruby_whisper_full_get_segment_text(VALUE self, VALUE i_segment)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   const int c_i_segment = ruby_whisper_full_check_segment_index(rw, i_segment);
   const char * text = whisper_full_get_segment_text(rw->context, c_i_segment);
   return rb_str_new2(text);
@@ -570,7 +570,7 @@ static VALUE
 ruby_whisper_full_get_segment_no_speech_prob(VALUE self, VALUE i_segment)
 {
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
   const int c_i_segment = ruby_whisper_full_check_segment_index(rw, i_segment);
   const float no_speech_prob = whisper_full_get_segment_no_speech_prob(rw->context, c_i_segment);
   return DBL2NUM(no_speech_prob);
@@ -611,7 +611,7 @@ ruby_whisper_each_segment(VALUE self)
   }
 
   ruby_whisper *rw;
-  TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(self, rw);
 
   const int n_segments = whisper_full_n_segments(rw->context);
   for (int i = 0; i < n_segments; ++i) {

data/ext/ruby_whisper_model.c

@@ -53,7 +53,7 @@ ruby_whisper_model_n_vocab(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_vocab(rw->context));
 }
 
@@ -67,7 +67,7 @@ ruby_whisper_model_n_audio_ctx(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_audio_ctx(rw->context));
 }
 
@@ -81,7 +81,7 @@ ruby_whisper_model_n_audio_state(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_audio_state(rw->context));
 }
 
@@ -95,7 +95,7 @@ ruby_whisper_model_n_audio_head(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_audio_head(rw->context));
 }
 
@@ -109,7 +109,7 @@ ruby_whisper_model_n_audio_layer(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_audio_layer(rw->context));
 }
 
@@ -123,7 +123,7 @@ ruby_whisper_model_n_text_ctx(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_text_ctx(rw->context));
 }
 
@@ -137,7 +137,7 @@ ruby_whisper_model_n_text_state(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_text_state(rw->context));
 }
 
@@ -151,7 +151,7 @@ ruby_whisper_model_n_text_head(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_text_head(rw->context));
 }
 
@@ -165,7 +165,7 @@ ruby_whisper_model_n_text_layer(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_text_layer(rw->context));
 }
 
@@ -179,7 +179,7 @@ ruby_whisper_model_n_mels(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_n_mels(rw->context));
 }
 
@@ -193,7 +193,7 @@ ruby_whisper_model_ftype(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return INT2NUM(whisper_model_ftype(rw->context));
 }
 
@@ -207,7 +207,7 @@ ruby_whisper_model_type(VALUE self)
   ruby_whisper_model *rwm;
   TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
   ruby_whisper *rw;
-  TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
+  GetContext(rwm->context, rw);
   return rb_str_new2(whisper_model_type_readable(rw->context));
 }
 

data/ext/ruby_whisper_params.c

@@ -26,7 +26,7 @@
   rb_define_method(cParams, #param_name, ruby_whisper_params_get_ ## param_name, 0); \
   rb_define_method(cParams, #param_name "=", ruby_whisper_params_set_ ## param_name, 1);
 
-#define RUBY_WHISPER_PARAMS_PARAM_NAMES_COUNT 36
+#define RUBY_WHISPER_PARAMS_PARAM_NAMES_COUNT 37
 
 extern VALUE cParams;
 extern VALUE cVADParams;
@@ -46,6 +46,7 @@ static ID id_print_special;
 static ID id_print_progress;
 static ID id_print_realtime;
 static ID id_print_timestamps;
+static ID id_carry_initial_prompt;
 static ID id_suppress_blank;
 static ID id_suppress_nst;
 static ID id_token_timestamps;
@@ -427,6 +428,7 @@ ruby_whisper_params_set_print_realtime(VALUE self, VALUE value)
 }
 /*
  * If true, prints results from within whisper.cpp. (avoid it, use callback instead)
+ *
  * call-seq:
  *   print_realtime -> bool
  */
@@ -455,6 +457,26 @@ ruby_whisper_params_get_print_timestamps(VALUE self)
 {
   BOOL_PARAMS_GETTER(self, print_timestamps)
 }
+
+/*
+ *  call-seq:
+ *    carry_initial_prompt -> true or false
+ */
+static VALUE
+ruby_whisper_params_get_carry_initial_prompt(VALUE self)
+{
+  BOOL_PARAMS_GETTER(self, carry_initial_prompt)
+}
+
+/*
+ *  call-seq:
+ *    carry_initial_prompt = bool -> bool
+ */
+static VALUE
+ruby_whisper_params_set_carry_initial_prompt(VALUE self, VALUE value)
+{
+  BOOL_PARAMS_SETTER(self, carry_initial_prompt, value)
+}
 /*
  * call-seq:
  *   suppress_blank = force_suppress -> force_suppress
@@ -1168,6 +1190,7 @@ ruby_whisper_params_initialize(int argc, VALUE *argv, VALUE self)
       SET_PARAM_IF_SAME(max_len)
       SET_PARAM_IF_SAME(split_on_word)
       SET_PARAM_IF_SAME(initial_prompt)
+      SET_PARAM_IF_SAME(carry_initial_prompt)
       SET_PARAM_IF_SAME(offset)
       SET_PARAM_IF_SAME(duration)
       SET_PARAM_IF_SAME(max_text_tokens)
@@ -1303,28 +1326,29 @@ init_ruby_whisper_params(VALUE *mWhisper)
   DEFINE_PARAM(max_len, 11)
   DEFINE_PARAM(split_on_word, 12)
   DEFINE_PARAM(initial_prompt, 13)
-  DEFINE_PARAM(diarize, 14)
-  DEFINE_PARAM(offset, 15)
-  DEFINE_PARAM(duration, 16)
-  DEFINE_PARAM(max_text_tokens, 17)
-  DEFINE_PARAM(temperature, 18)
-  DEFINE_PARAM(max_initial_ts, 19)
-  DEFINE_PARAM(length_penalty, 20)
-  DEFINE_PARAM(temperature_inc, 21)
-  DEFINE_PARAM(entropy_thold, 22)
-  DEFINE_PARAM(logprob_thold, 23)
-  DEFINE_PARAM(no_speech_thold, 24)
-  DEFINE_PARAM(new_segment_callback, 25)
-  DEFINE_PARAM(new_segment_callback_user_data, 26)
-  DEFINE_PARAM(progress_callback, 27)
-  DEFINE_PARAM(progress_callback_user_data, 28)
-  DEFINE_PARAM(encoder_begin_callback, 29)
-  DEFINE_PARAM(encoder_begin_callback_user_data, 30)
-  DEFINE_PARAM(abort_callback, 31)
-  DEFINE_PARAM(abort_callback_user_data, 32)
-  DEFINE_PARAM(vad, 33)
-  DEFINE_PARAM(vad_model_path, 34)
-  DEFINE_PARAM(vad_params, 35)
+  DEFINE_PARAM(carry_initial_prompt, 14)
+  DEFINE_PARAM(diarize, 15)
+  DEFINE_PARAM(offset, 16)
+  DEFINE_PARAM(duration, 17)
+  DEFINE_PARAM(max_text_tokens, 18)
+  DEFINE_PARAM(temperature, 19)
+  DEFINE_PARAM(max_initial_ts, 20)
+  DEFINE_PARAM(length_penalty, 21)
+  DEFINE_PARAM(temperature_inc, 22)
+  DEFINE_PARAM(entropy_thold, 23)
+  DEFINE_PARAM(logprob_thold, 24)
+  DEFINE_PARAM(no_speech_thold, 25)
+  DEFINE_PARAM(new_segment_callback, 26)
+  DEFINE_PARAM(new_segment_callback_user_data, 27)
+  DEFINE_PARAM(progress_callback, 28)
+  DEFINE_PARAM(progress_callback_user_data, 29)
+  DEFINE_PARAM(encoder_begin_callback, 30)
+  DEFINE_PARAM(encoder_begin_callback_user_data, 31)
+  DEFINE_PARAM(abort_callback, 32)
+  DEFINE_PARAM(abort_callback_user_data, 33)
+  DEFINE_PARAM(vad, 34)
+  DEFINE_PARAM(vad_model_path, 35)
+  DEFINE_PARAM(vad_params, 36)
 
   rb_define_method(cParams, "on_new_segment", ruby_whisper_params_on_new_segment, 0);
   rb_define_method(cParams, "on_progress", ruby_whisper_params_on_progress, 0);