ruby : add VAD::Context#segments_from_samples, allow Pathname, etc.

bindings/ruby/README.md

@@ -323,7 +323,24 @@ whisper
   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.
+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.
+
+```ruby
+require "torchaudio"
+require "arrow-numo-narray"
+require "whisper"
+
+waveform, sample_rate = TorchAudio.load("test/fixtures/jfk.wav")
+# Convert Torch::Tensor to Arrow::Array via Numo::NArray
+samples = waveform.squeeze.numo.to_arrow.to_arrow_array
+
+whisper = Whisper::Context.new("base")
+whisper
+  # Arrow::Array exports MemoryView
+  .full(Whisper::Params.new, samples)
+```
 
 Using VAD separately from ASR
 -----------------------------
@@ -334,13 +351,27 @@ VAD feature itself is useful. You can use it separately from ASR:
 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|
+  .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
 ```
 
+You may also low level API `Whisper::VAD::Context#segments_from_samples` as such `Whisper::Context#full`:
+
+```ruby
+# Ruby Array
+reader = WaveFile::Reader.new("path/to/audio.wav", WaveFile::Format.new(:mono, :float, 16000))
+samples = reader.enum_for(:each_buffer).map(&:samples).flatten
+
+# Or, object which exports MemoryView
+waveform, sample_rate = TorchAudio.load("test/fixtures/jfk.wav")
+samples = waveform.squeeze.numo.to_arrow.to_arrow_array
+
+segments = vad.segments_from_samples(Whisper::VAD::Params.new, samples)
+```
+
 Development
 -----------
 

bindings/ruby/ext/extconf.rb

@@ -7,6 +7,7 @@
 have_library("gomp") rescue nil
 libs = Dependencies.new(cmake, options).to_s
 
+$CFLAGS << " -O3 -march=native"
 $INCFLAGS << " -Isources/include -Isources/ggml/include -Isources/examples"
 $LOCAL_LIBS << " #{libs}"
 $cleanfiles << " build #{libs}"

bindings/ruby/ext/ruby_whisper.c

@@ -1,5 +1,3 @@
-#include <ruby.h>
-#include <ruby/memory_view.h>
 #include "ruby_whisper.h"
 
 VALUE mWhisper;

bindings/ruby/ext/ruby_whisper.h

@@ -1,6 +1,8 @@
 #ifndef RUBY_WHISPER_H
 #define RUBY_WHISPER_H
 
+#include <ruby.h>
+#include <ruby/memory_view.h>
 #include "whisper.h"
 
 typedef struct {
@@ -55,6 +57,13 @@ typedef struct {
   struct whisper_vad_context *context;
 } ruby_whisper_vad_context;
 
+typedef struct parsed_samples_t {
+  float *samples;
+  int n_samples;
+  rb_memory_view_t memview;
+  bool memview_exported;
+} parsed_samples_t;
+
 #define GetContext(obj, rw) do { \
   TypedData_Get_Struct((obj), ruby_whisper, &ruby_whisper_type, (rw)); \
   if ((rw)->context == NULL) { \
@@ -69,6 +78,17 @@ typedef struct {
   } \
 } while (0)
 
+#define GetVADContext(obj, rwvc) do { \
+    TypedData_Get_Struct((obj), ruby_whisper_vad_context, &ruby_whisper_vad_context_type, (rwvc)); \
+    if ((rwvc)->context == NULL) { \
+      rb_raise(rb_eRuntimeError, "Not initialized"); \
+    } \
+} while (0)
+
+#define GetVADParams(obj, rwvp) do { \
+  TypedData_Get_Struct((obj), ruby_whisper_vad_params, &ruby_whisper_vad_params_type, (rwvp)); \
+} 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) { \