ruby : Make context accept initial parameters, API to retrieve a segment and more

bindings/ruby/README.md

@@ -24,14 +24,15 @@ require "whisper"
 
 whisper = Whisper::Context.new("base")
 
-params = Whisper::Params.new
-params.language = "en"
-params.offset = 10_000
-params.duration = 60_000
-params.max_text_tokens = 300
-params.translate = true
-params.print_timestamps = false
-params.initial_prompt = "Initial prompt here."
+params = Whisper::Params.new(
+  language: "en",
+  offset: 10_000,
+  duration: 60_000,
+  max_text_tokens: 300,
+  translate: true,
+  print_timestamps: false,
+  initial_prompt: "Initial prompt here."
+)
 
 whisper.transcribe("path/to/audio.wav", params) do |whole_text|
   puts whole_text
@@ -113,18 +114,18 @@ def format_time(time_ms)
   "%02d:%02d:%02d.%03d" % [hour, min, sec, decimal_part]
 end
 
-whisper.transcribe("path/to/audio.wav", params)
-
-whisper.each_segment.with_index do |segment, index|
-  line = "[%{nth}: %{st} --> %{ed}] %{text}" % {
-    nth: index + 1,
-    st: format_time(segment.start_time),
-    ed: format_time(segment.end_time),
-    text: segment.text
-  }
-  line << " (speaker turned)" if segment.speaker_next_turn?
-  puts line
-end
+whisper
+  .transcribe("path/to/audio.wav", params)
+  .each_segment.with_index do |segment, index|
+    line = "[%{nth}: %{st} --> %{ed}] %{text}" % {
+      nth: index + 1,
+      st: format_time(segment.start_time),
+      ed: format_time(segment.end_time),
+      text: segment.text
+    }
+    line << " (speaker turned)" if segment.speaker_next_turn?
+    puts line
+  end
 
 ```
 
@@ -215,10 +216,11 @@ reader = WaveFile::Reader.new("path/to/audio.wav", WaveFile::Format.new(:mono, :
 samples = reader.enum_for(:each_buffer).map(&:samples).flatten
 
 whisper = Whisper::Context.new("base")
-whisper.full(Whisper::Params.new, samples)
-whisper.each_segment do |segment|
-  puts segment.text
-end
+whisper
+  .full(Whisper::Params.new, samples)
+  .each_segment do |segment|
+    puts segment.text
+  end
 ```
 
 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.

bindings/ruby/Rakefile

@@ -18,9 +18,11 @@ EXTSOURCES.each do |src|
 end
 
 CLEAN.include SOURCES
-CLEAN.include FileList["ext/*.o", "ext/*.metal", "ext/whisper.{so,bundle,dll}"]
+CLEAN.include FileList["ext/**/*.o", "ext/**/*.metal", "ext/**/*.tmp", "ext/whisper.{so,bundle,dll}"]
 
-task build: ["ext/Makefile", "ext/ruby_whisper.h", "ext/ruby_whisper.cpp", "whispercpp.gemspec"]
+SRC = FileList["ext/*.{c,cpp,h}"]
+
+task build: SOURCES
 
 directory "pkg"
 CLOBBER.include "pkg"
@@ -29,14 +31,14 @@ LIB_NAME = "whisper".ext(RbConfig::CONFIG["DLEXT"])
 SO_FILE = File.join("ext", LIB_NAME)
 LIB_FILE = File.join("lib", LIB_NAME)
 
-file "ext/Makefile" => ["ext/extconf.rb", "ext/ruby_whisper.h", "ext/ruby_whisper.cpp"] + SOURCES do |t|
-  Dir.chdir "ext" do
+file "ext/Makefile" => SRC + ["ext/extconf.rb"] + SOURCES do |t|
+  chdir "ext" do
     ruby "extconf.rb"
   end
 end
 
 file SO_FILE => "ext/Makefile" do |t|
-  Dir.chdir "ext" do
+  chdir "ext" do
     sh "make"
   end
 end
@@ -54,7 +56,7 @@ end
 
 TEST_MEMORY_VIEW = "tests/jfk_reader/jfk_reader.#{RbConfig::CONFIG['DLEXT']}"
 file TEST_MEMORY_VIEW => "tests/jfk_reader/jfk_reader.c" do |t|
-  Dir.chdir "tests/jfk_reader" do
+  chdir "tests/jfk_reader" do
     ruby "extconf.rb"
     sh "make"
   end

bindings/ruby/ext/.gitignore

@@ -4,10 +4,8 @@ whisper.bundle
 whisper.dll
 scripts/get-flags.mk
 *.o
-*.c
-*.cpp
-*.h
-*.m
-*.metal
-!ruby_whisper.cpp
-!ruby_whisper.h
+/*/**/*.c
+/*/**/*.cpp
+/*/**/*.h
+/*/**/*.m
+/*/**/*.metal

bindings/ruby/ext/extconf.rb

@@ -174,7 +174,14 @@
   'src/whisper.o'
 
 $objs = $OBJ_GGML + $OBJ_WHISPER + $OBJ_COMMON + $OBJ_SDL
-$objs << "ruby_whisper.o"
+$objs <<
+  "ruby_whisper.o" <<
+  "ruby_whisper_context.o" <<
+  "ruby_whisper_transcribe.o" <<
+  "ruby_whisper_params.o" <<
+  "ruby_whisper_error.o" <<
+  "ruby_whisper_segment.o" <<
+  "ruby_whisper_model.o"
 
 $CPPFLAGS  = "#{$MK_CPPFLAGS} #{$CPPFLAGS}"
 $CFLAGS    = "#{$CPPFLAGS} #{$MK_CFLAGS} #{$GF_CFLAGS} #{$CFLAGS}"

bindings/ruby/ext/ruby_whisper.c

@@ -0,0 +1,164 @@
+#include <ruby.h>
+#include <ruby/memory_view.h>
+#include "ruby_whisper.h"
+
+VALUE mWhisper;
+VALUE cContext;
+VALUE cParams;
+VALUE eError;
+
+VALUE cSegment;
+VALUE cModel;
+
+ID id_to_s;
+ID id_call;
+ID id___method__;
+ID id_to_enum;
+ID id_length;
+ID id_next;
+ID id_new;
+ID id_to_path;
+ID id_URI;
+ID id_pre_converted_models;
+
+static bool is_log_callback_finalized = false;
+
+// High level API
+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_model(VALUE *mWhisper);
+extern void register_callbacks(ruby_whisper_params *rwp, VALUE *context);
+
+/*
+ * call-seq:
+ *   lang_max_id -> Integer
+ */
+static VALUE ruby_whisper_s_lang_max_id(VALUE self) {
+  return INT2NUM(whisper_lang_max_id());
+}
+
+/*
+ * call-seq:
+ *   lang_id(lang_name) -> Integer
+ */
+static VALUE ruby_whisper_s_lang_id(VALUE self, VALUE lang) {
+  const char * lang_str = StringValueCStr(lang);
+  const int id = whisper_lang_id(lang_str);
+  if (-1 == id) {
+    rb_raise(rb_eArgError, "language not found: %s", lang_str);
+  }
+  return INT2NUM(id);
+}
+
+/*
+ * call-seq:
+ *   lang_str(lang_id) -> String
+ */
+static VALUE ruby_whisper_s_lang_str(VALUE self, VALUE id) {
+  const int lang_id = NUM2INT(id);
+  const char * str = whisper_lang_str(lang_id);
+  if (NULL == str) {
+    rb_raise(rb_eIndexError, "id %d outside of language id", lang_id);
+  }
+  return rb_str_new2(str);
+}
+
+/*
+ * call-seq:
+ *   lang_str(lang_id) -> String
+ */
+static VALUE ruby_whisper_s_lang_str_full(VALUE self, VALUE id) {
+  const int lang_id = NUM2INT(id);
+  const char * str_full = whisper_lang_str_full(lang_id);
+  if (NULL == str_full) {
+    rb_raise(rb_eIndexError, "id %d outside of language id", lang_id);
+  }
+  return rb_str_new2(str_full);
+}
+
+static VALUE ruby_whisper_s_finalize_log_callback(VALUE self, VALUE id) {
+  is_log_callback_finalized = true;
+  return Qnil;
+}
+
+static void
+ruby_whisper_log_callback(enum ggml_log_level level, const char * buffer, void * user_data) {
+  if (is_log_callback_finalized) {
+    return;
+  }
+  VALUE log_callback = rb_iv_get(mWhisper, "log_callback");
+  VALUE udata = rb_iv_get(mWhisper, "user_data");
+  rb_funcall(log_callback, id_call, 3, INT2NUM(level), rb_str_new2(buffer), udata);
+}
+
+/*
+ * call-seq:
+ *   log_set ->(level, buffer, user_data) { ... }, user_data -> nil
+ */
+static VALUE ruby_whisper_s_log_set(VALUE self, VALUE log_callback, VALUE user_data) {
+  VALUE old_callback = rb_iv_get(self, "log_callback");
+  if (!NIL_P(old_callback)) {
+    rb_undefine_finalizer(old_callback);
+  }
+
+  rb_iv_set(self, "log_callback", log_callback);
+  rb_iv_set(self, "user_data", user_data);
+
+  VALUE finalize_log_callback = rb_funcall(mWhisper, rb_intern("method"), 1, rb_str_new2("finalize_log_callback"));
+  rb_define_finalizer(log_callback, finalize_log_callback);
+
+  whisper_log_set(ruby_whisper_log_callback, NULL);
+
+  return Qnil;
+}
+
+static void rb_whisper_model_mark(ruby_whisper_model *rwm) {
+  rb_gc_mark(rwm->context);
+}
+
+static VALUE ruby_whisper_model_allocate(VALUE klass) {
+  ruby_whisper_model *rwm;
+  rwm = ALLOC(ruby_whisper_model);
+  return Data_Wrap_Struct(klass, rb_whisper_model_mark, RUBY_DEFAULT_FREE, rwm);
+}
+
+void Init_whisper() {
+  id_to_s = rb_intern("to_s");
+  id_call = rb_intern("call");
+  id___method__ = rb_intern("__method__");
+  id_to_enum = rb_intern("to_enum");
+  id_length = rb_intern("length");
+  id_next = rb_intern("next");
+  id_new = rb_intern("new");
+  id_to_path = rb_intern("to_path");
+  id_URI = rb_intern("URI");
+  id_pre_converted_models = rb_intern("pre_converted_models");
+
+  mWhisper = rb_define_module("Whisper");
+
+  rb_define_const(mWhisper, "LOG_LEVEL_NONE", INT2NUM(GGML_LOG_LEVEL_NONE));
+  rb_define_const(mWhisper, "LOG_LEVEL_INFO", INT2NUM(GGML_LOG_LEVEL_INFO));
+  rb_define_const(mWhisper, "LOG_LEVEL_WARN", INT2NUM(GGML_LOG_LEVEL_WARN));
+  rb_define_const(mWhisper, "LOG_LEVEL_ERROR", INT2NUM(GGML_LOG_LEVEL_ERROR));
+  rb_define_const(mWhisper, "LOG_LEVEL_DEBUG", INT2NUM(GGML_LOG_LEVEL_DEBUG));
+  rb_define_const(mWhisper, "LOG_LEVEL_CONT", INT2NUM(GGML_LOG_LEVEL_CONT));
+
+  rb_define_singleton_method(mWhisper, "lang_max_id", ruby_whisper_s_lang_max_id, 0);
+  rb_define_singleton_method(mWhisper, "lang_id", ruby_whisper_s_lang_id, 1);
+  rb_define_singleton_method(mWhisper, "lang_str", ruby_whisper_s_lang_str, 1);
+  rb_define_singleton_method(mWhisper, "lang_str_full", ruby_whisper_s_lang_str_full, 1);
+  rb_define_singleton_method(mWhisper, "log_set", ruby_whisper_s_log_set, 2);
+  rb_define_private_method(rb_singleton_class(mWhisper), "finalize_log_callback", ruby_whisper_s_finalize_log_callback, 1);
+
+  init_ruby_whisper_context(&mWhisper);
+  init_ruby_whisper_params(&mWhisper);
+  init_ruby_whisper_error(&mWhisper);
+  init_ruby_whisper_segment(&mWhisper, &cContext);
+  init_ruby_whisper_model(&mWhisper);
+
+  rb_require("whisper/model/uri");
+}