ruby : Add parallel transcription support (#3222)

* Fix indentation of code sample in document comment

* Make Whisper::Context#transcribe able to run non-parallel

* Add test for Whisper::Context#transcribe with parallel option

* Follow signature API change of Context#transcribe

* Remove useless variable assignment

* Move simple usage up in README

* Add need help section in README

* Add document on Context#transcribe's parallel option in README

* Update date

* Fix signature of Context.new

* Make Context#subscribe accept n_processors option

* Make test follow #transcribe's change

* Make RBS follow #transcribe's change

* Add document for #transcribe's n_processors option

* Rename test directory so that Rake tasks' default setting is used

bindings/ruby/ext/ruby_whisper.c

@@ -24,6 +24,7 @@ ID id_URI;
 ID id_pre_converted_models;
 ID id_coreml_compiled_models;
 ID id_cache;
+ID id_n_processors;
 
 static bool is_log_callback_finalized = false;
 
@@ -142,6 +143,7 @@ void Init_whisper() {
   id_pre_converted_models = rb_intern("pre_converted_models");
   id_coreml_compiled_models = rb_intern("coreml_compiled_models");
   id_cache = rb_intern("cache");
+  id_n_processors = rb_intern("n_processors");
 
   mWhisper = rb_define_module("Whisper");
   mVAD = rb_define_module_under(mWhisper, "VAD");

bindings/ruby/ext/ruby_whisper_context.c

@@ -13,6 +13,7 @@ extern ID id_URI;
 extern ID id_pre_converted_models;
 extern ID id_coreml_compiled_models;
 extern ID id_cache;
+extern ID id_n_processors;
 
 extern VALUE cContext;
 extern VALUE eError;
@@ -24,6 +25,8 @@ extern VALUE rb_whisper_model_s_new(VALUE context);
 extern VALUE rb_whisper_segment_s_new(VALUE context, int index);
 extern void prepare_transcription(ruby_whisper_params *rwp, VALUE *context);
 
+ID transcribe_option_names[1];
+
 static void
 ruby_whisper_free(ruby_whisper *rw)
 {
@@ -633,6 +636,8 @@ init_ruby_whisper_context(VALUE *mWhisper)
 {
   cContext = rb_define_class_under(*mWhisper, "Context", rb_cObject);
 
+  transcribe_option_names[0] = id_n_processors;
+
   rb_define_alloc_func(cContext, ruby_whisper_allocate);
   rb_define_method(cContext, "initialize", ruby_whisper_initialize, -1);
 

bindings/ruby/ext/ruby_whisper_transcribe.cpp

@@ -13,6 +13,7 @@ extern const rb_data_type_t ruby_whisper_params_type;
 
 extern ID id_to_s;
 extern ID id_call;
+extern ID transcribe_option_names[1];
 
 extern void
 prepare_transcription(ruby_whisper_params * rwp, VALUE * self);
@@ -34,9 +35,14 @@ VALUE
 ruby_whisper_transcribe(int argc, VALUE *argv, VALUE self) {
   ruby_whisper *rw;
   ruby_whisper_params *rwp;
-  VALUE wave_file_path, blk, params;
+  VALUE wave_file_path, blk, params, kws;
+  VALUE opts[1];
+
+  rb_scan_args_kw(RB_SCAN_ARGS_LAST_HASH_KEYWORDS, argc, argv, "2:&", &wave_file_path, &params, &kws, &blk);
+  rb_get_kwargs(kws, transcribe_option_names, 0, 1, opts);
+
+  int n_processors = opts[0] == Qundef ? 1 : NUM2INT(opts[0]);
 
-  rb_scan_args(argc, argv, "02&", &wave_file_path, &params, &blk);
   TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
   TypedData_Get_Struct(params, ruby_whisper_params, &ruby_whisper_params_type, rwp);
 
@@ -66,7 +72,7 @@ ruby_whisper_transcribe(int argc, VALUE *argv, VALUE self) {
 
   prepare_transcription(rwp, &self);
 
-  if (whisper_full_parallel(rw->context, rwp->params, pcmf32.data(), pcmf32.size(), 1) != 0) {
+  if (whisper_full_parallel(rw->context, rwp->params, pcmf32.data(), pcmf32.size(), n_processors) != 0) {
     fprintf(stderr, "failed to process audio\n");
     return self;
   }
@@ -76,9 +82,8 @@ ruby_whisper_transcribe(int argc, VALUE *argv, VALUE self) {
     const char * text = whisper_full_get_segment_text(rw->context, i);
     output = rb_str_concat(output, rb_str_new2(text));
   }
-  VALUE idCall = id_call;
   if (blk != Qnil) {
-    rb_funcall(blk, idCall, 1, output);
+    rb_funcall(blk, id_call, 1, output);
   }
   return self;
 }