Merge branch 'master' into allow-for-NextSegment-to-be-called-when-Process-is-re-called

Author: joshmux

README.md

@@ -362,6 +362,7 @@ First, check if your Ascend NPU device is supported:
 | Ascend NPU                    | Status  |
 |:-----------------------------:|:-------:|
 | Atlas 300T A2                 | Support |
+| Atlas 300I Duo                | Support |
 
 Then, make sure you have installed [`CANN toolkit`](https://www.hiascend.com/en/software/cann/community) . The lasted version of CANN is recommanded.
 
@@ -755,23 +756,23 @@ written in Python that is fast and accurate.
 
 Models can be downloaded by running the following command on Linux or MacOS:
 ```console
-$ ./models/download-vad-model.sh silero-v5.1.2
-Downloading ggml model silero-v5.1.2 from 'https://huggingface.co/ggml-org/whisper-vad' ...
-ggml-silero-v5.1.2.bin        100%[==============================================>] 864.35K  --.-KB/s    in 0.04s
-Done! Model 'silero-v5.1.2' saved in '/path/models/ggml-silero-v5.1.2.bin'
+$ ./models/download-vad-model.sh silero-v6.2.0
+Downloading ggml model silero-v6.2.0 from 'https://huggingface.co/ggml-org/whisper-vad' ...
+ggml-silero-v6.2.0.bin        100%[==============================================>] 864.35K  --.-KB/s    in 0.04s
+Done! Model 'silero-v6.2.0' saved in '/path/models/ggml-silero-v6.2.0.bin'
 You can now use it like this:
 
-  $ ./build/bin/whisper-cli -vm /path/models/ggml-silero-v5.1.2.bin --vad -f samples/jfk.wav -m models/ggml-base.en.bin
+  $ ./build/bin/whisper-cli -vm /path/models/ggml-silero-v6.2.0.bin --vad -f samples/jfk.wav -m models/ggml-base.en.bin
 
 ```
 And the following command on Windows:
 ```console
-> .\models\download-vad-model.cmd silero-v5.1.2
-Downloading vad model silero-v5.1.2...
-Done! Model silero-v5.1.2 saved in C:\Users\danie\work\ai\whisper.cpp\ggml-silero-v5.1.2.bin
+> .\models\download-vad-model.cmd silero-v6.2.0
+Downloading vad model silero-v6.2.0...
+Done! Model silero-v6.2.0 saved in C:\Users\danie\work\ai\whisper.cpp\ggml-silero-v6.2.0.bin
 You can now use it like this:
 
-C:\path\build\bin\Release\whisper-cli.exe -vm C:\path\ggml-silero-v5.1.2.bin --vad -m models/ggml-base.en.bin -f samples\jfk.wav
+C:\path\build\bin\Release\whisper-cli.exe -vm C:\path\ggml-silero-v6.2.0.bin --vad -m models/ggml-base.en.bin -f samples\jfk.wav
 
 ```
 
@@ -783,15 +784,15 @@ This model can be also be converted manually to ggml using the following command
 $ python3 -m venv venv && source venv/bin/activate
 $ (venv) pip install silero-vad
 $ (venv) $ python models/convert-silero-vad-to-ggml.py --output models/silero.bin
-Saving GGML Silero-VAD model to models/silero-v5.1.2-ggml.bin
+Saving GGML Silero-VAD model to models/silero-v6.2.0-ggml.bin
 ```
 And it can then be used with whisper as follows:
 ```console
 $ ./build/bin/whisper-cli \
    --file ./samples/jfk.wav \
    --model ./models/ggml-base.en.bin \
    --vad \
-   --vad-model ./models/silero-v5.1.2-ggml.bin
+   --vad-model ./models/silero-v6.2.0-ggml.bin
 ```
 
 ### VAD Options

bindings/ruby/README.md

@@ -134,20 +134,20 @@ 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
@@ -324,6 +324,22 @@ 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
 -----------
 

bindings/ruby/ext/ruby_whisper.c

@@ -6,7 +6,10 @@ VALUE mWhisper;
 VALUE mVAD;
 VALUE cContext;
 VALUE cParams;
+VALUE cVADContext;
 VALUE cVADParams;
+VALUE cVADSegments;
+VALUE cVADSegment;
 VALUE eError;
 
 VALUE cSegment;
@@ -37,6 +40,9 @@ 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 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);
 
 /*
@@ -170,6 +176,9 @@ void Init_whisper() {
   init_ruby_whisper_segment(&mWhisper, &cContext);
   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");

bindings/ruby/ext/ruby_whisper.h

@@ -37,4 +37,17 @@ 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;
+
 #endif

bindings/ruby/ext/ruby_whisper_segment.c

@@ -29,6 +29,9 @@ ruby_whisper_segment_memsize(const void *p)
   if (!rws) {
     return 0;
   }
+  if (rws->index) {
+    size += sizeof(rws->index);
+  }
   return size;
 }
 

bindings/ruby/ext/ruby_whisper_vad_context.c

@@ -0,0 +1,75 @@
+#include <ruby.h>
+#include "ruby_whisper.h"
+
+extern ID id_to_s;
+
+extern VALUE cVADContext;
+
+extern VALUE ruby_whisper_vad_detect(VALUE self, VALUE file_path, VALUE params);
+extern VALUE ruby_whisper_normalize_model_path(VALUE model_path);
+
+static size_t
+ruby_whisper_vad_context_memsize(const void *p)
+{
+  const ruby_whisper_vad_context *rwvc = p;
+  size_t size = sizeof(rwvc);
+  if (!rwvc) {
+    return 0;
+  }
+  if (rwvc->context) {
+    size += sizeof(rwvc->context);
+  }
+  return size;
+}
+
+static void
+ruby_whisper_vad_context_free(void *p)
+{
+  ruby_whisper_vad_context *rwvc = (ruby_whisper_vad_context *)p;
+  if (rwvc->context) {
+    whisper_vad_free(rwvc->context);
+    rwvc->context = NULL;
+  }
+  xfree(rwvc);
+}
+
+const rb_data_type_t ruby_whisper_vad_context_type = {
+  "ruby_whisper_vad_context",
+  {0, ruby_whisper_vad_context_free, ruby_whisper_vad_context_memsize,},
+  0, 0,
+  0
+};
+
+static VALUE
+ruby_whisper_vad_context_s_allocate(VALUE klass)
+{
+  ruby_whisper_vad_context *rwvc;
+  VALUE obj = TypedData_Make_Struct(klass, ruby_whisper_vad_context, &ruby_whisper_vad_context_type, rwvc);
+  rwvc->context = NULL;
+  return obj;
+}
+
+static VALUE
+ruby_whisper_vad_context_initialize(VALUE self, VALUE model_path)
+{
+  ruby_whisper_vad_context *rwvc;
+  struct whisper_vad_context *context;
+
+  model_path = ruby_whisper_normalize_model_path(model_path);
+  context = whisper_vad_init_from_file_with_params(StringValueCStr(model_path), whisper_vad_default_context_params());
+  if (context == NULL) {
+    rb_raise(rb_eRuntimeError, "Failed to initialize whisper VAD context");
+  }
+  TypedData_Get_Struct(self, ruby_whisper_vad_context, &ruby_whisper_vad_context_type, rwvc);
+  rwvc->context = context;
+
+  return Qnil;
+}
+
+void init_ruby_whisper_vad_context(VALUE *mVAD)
+{
+  cVADContext = rb_define_class_under(*mVAD, "Context", rb_cObject);
+  rb_define_alloc_func(cVADContext, ruby_whisper_vad_context_s_allocate);
+  rb_define_method(cVADContext, "initialize", ruby_whisper_vad_context_initialize, 1);
+  rb_define_method(cVADContext, "detect", ruby_whisper_vad_detect, 2);
+}

bindings/ruby/ext/ruby_whisper_vad_context_detect.cpp

@@ -0,0 +1,50 @@
+#include <ruby.h>
+#include "ruby_whisper.h"
+#include "common-whisper.h"
+#include <string>
+#include <vector>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+extern VALUE cVADSegments;
+
+extern const rb_data_type_t ruby_whisper_vad_context_type;
+extern const rb_data_type_t ruby_whisper_vad_params_type;
+extern const rb_data_type_t ruby_whisper_vad_segments_type;
+
+extern VALUE ruby_whisper_vad_segments_s_init(struct whisper_vad_segments *segments);
+
+VALUE
+ruby_whisper_vad_detect(VALUE self, VALUE file_path, VALUE params) {
+  ruby_whisper_vad_context *rwvc;
+  ruby_whisper_vad_params *rwvp;
+  std::string cpp_file_path;
+  std::vector<float> pcmf32;
+  std::vector<std::vector<float>> pcmf32s;
+  whisper_vad_segments *segments;
+
+  TypedData_Get_Struct(self, ruby_whisper_vad_context, &ruby_whisper_vad_context_type, rwvc);
+  if (rwvc->context == NULL) {
+    rb_raise(rb_eRuntimeError, "Doesn't have referenxe to context internally");
+  }
+  TypedData_Get_Struct(params, ruby_whisper_vad_params, &ruby_whisper_vad_params_type, rwvp);
+
+  cpp_file_path = StringValueCStr(file_path);
+
+  if (!read_audio_data(cpp_file_path, pcmf32, pcmf32s, false)) {
+    rb_raise(rb_eRuntimeError, "Failed to open '%s' as WAV file\n", cpp_file_path.c_str());
+  }
+
+  segments = whisper_vad_segments_from_samples(rwvc->context, rwvp->params, pcmf32.data(), pcmf32.size());
+  if (segments == nullptr) {
+    rb_raise(rb_eRuntimeError, "Failed to process audio\n");
+  }
+
+  return ruby_whisper_vad_segments_s_init(segments);
+}
+
+#ifdef __cplusplus
+}
+#endif