vad : Silero VAD v6.2.0 (#3524)

* Add ggml-silero-v6.2.0 to download candidates

* Make default VAD model ggml-silero-v6.2.0

* Make VAD model in documentations ggml-silero-v6.2.0

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
@@ -330,7 +330,7 @@ Using VAD separately from ASR
 VAD feature itself is useful. You can use it separately from ASR:
 
 ```ruby
-vad = Whisper::VAD::Context.new("silero-v5.1.2")
+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|

bindings/ruby/lib/whisper/model/uri.rb

@@ -206,6 +206,7 @@ module Whisper
 
     %w[
       silero-v5.1.2
+      silero-v6.2.0
     ].each do |name|
       @pre_converted_models[name] = URI.new("https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-#{name}.bin")
     end

bindings/ruby/test/test_params.rb

@@ -218,12 +218,12 @@ class TestParams < TestBase
 
   def test_vad_model_path
     assert_nil @params.vad_model_path
-    @params.vad_model_path = "silero-v5.1.2"
-    assert_equal Whisper::Model.pre_converted_models["silero-v5.1.2"].to_path, @params.vad_model_path
+    @params.vad_model_path = "silero-v6.2.0"
+    assert_equal Whisper::Model.pre_converted_models["silero-v6.2.0"].to_path, @params.vad_model_path
   end
 
   def test_vad_model_path_with_nil
-    @params.vad_model_path = "silero-v5.1.2"
+    @params.vad_model_path = "silero-v6.2.0"
     @params.vad_model_path = nil
     assert_nil @params.vad_model_path
   end
@@ -235,13 +235,13 @@ class TestParams < TestBase
   end
 
   def test_vad_model_path_with_URI_string
-    @params.vad_model_path = "https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v5.1.2.bin"
-    assert_equal @params.vad_model_path, Whisper::Model.pre_converted_models["silero-v5.1.2"].to_path
+    @params.vad_model_path = "https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v6.2.0.bin"
+    assert_equal @params.vad_model_path, Whisper::Model.pre_converted_models["silero-v6.2.0"].to_path
   end
 
   def test_vad_model_path_with_URI
-    @params.vad_model_path = URI("https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v5.1.2.bin")
-    assert_equal @params.vad_model_path, Whisper::Model.pre_converted_models["silero-v5.1.2"].to_path
+    @params.vad_model_path = URI("https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v6.2.0.bin")
+    assert_equal @params.vad_model_path, Whisper::Model.pre_converted_models["silero-v6.2.0"].to_path
   end
 
   def test_vad_params
@@ -289,7 +289,7 @@ class TestParams < TestBase
             in [/_user_data\Z/, *]
               Object.new
             in [:vad_model_path, *]
-              Whisper::Model.pre_converted_models["silero-v5.1.2"].to_path
+              Whisper::Model.pre_converted_models["silero-v6.2.0"].to_path
             in [:vad_params, *]
               Whisper::VAD::Params.new
             end

bindings/ruby/test/test_vad.rb

@@ -6,7 +6,7 @@ class TestVAD < TestBase
     vad_params = Whisper::VAD::Params.new
     @params = Whisper::Params.new(
       vad: true,
-      vad_model_path: "silero-v5.1.2",
+      vad_model_path: "silero-v6.2.0",
       vad_params:
     )
   end

bindings/ruby/test/test_vad_context.rb

@@ -2,12 +2,12 @@ require_relative "helper"
 
 class TestVADContext < TestBase
   def test_initialize
-    context = Whisper::VAD::Context.new("silero-v5.1.2")
+    context = Whisper::VAD::Context.new("silero-v6.2.0")
     assert_instance_of Whisper::VAD::Context, context
   end
 
   def test_detect
-    context = Whisper::VAD::Context.new("silero-v5.1.2")
+    context = Whisper::VAD::Context.new("silero-v6.2.0")
     segments = context.detect(AUDIO, Whisper::VAD::Params.new)
     assert_instance_of Whisper::VAD::Segments, segments
 
@@ -32,7 +32,7 @@ class TestVADContext < TestBase
     assert_equal segment.start_time, start_time
     assert_equal segment.end_time, end_time
 
-    assert_equal 5, segments.length
+    assert_equal 4, segments.length
   end
 
   def test_invalid_model_type