Update version

README.md

@@ -95,8 +95,8 @@ Run like this:
 
 ```
 cd vosk-api/python/example
-wget https://github.com/alphacep/kaldi-android-demo/releases/download/2020-01/alphacep-model-android-en-us-0.3.tar.gz
-tar xf alphacep-model-android-en-us-0.3.tar.gz 
+wget https://alphacephei.com/kaldi/models/vosk-model-small-en-us-0.3.zip
+unzip alphacep-model-android-en-us-0.3.zip
 mv alphacep-model-android-en-us-0.3 model-en
 python3 ./test_simple.py test.wav
 ```
@@ -111,8 +111,8 @@ Or Java
 
 ```
 cd java && KALDI_ROOT=<KALDI_ROOT> make
-wget https://github.com/alphacep/kaldi-android-demo/releases/download/2020-01/alphacep-model-android-en-us-0.3.tar.gz
-tar xf alphacep-model-android-en-us-0.3.tar.gz 
+wget https://alphacephei.com/kaldi/models/vosk-model-small-en-us-0.3.zip
+unzip alphacep-model-android-en-us-0.3.zip
 mv alphacep-model-android-en-us-0.3 model
 make run
 ```
@@ -123,8 +123,8 @@ Or C#
 
 ```
 cd csharp && KALDI_ROOT=<KALDI_ROOT> make
-wget https://github.com/alphacep/kaldi-android-demo/releases/download/2020-01/alphacep-model-android-en-us-0.3.tar.gz
-tar xf alphacep-model-android-en-us-0.3.tar.gz 
+wget https://alphacephei.com/kaldi/models/vosk-model-small-en-us-0.3.zip
+unzip alphacep-model-android-en-us-0.3.zip
 mv alphacep-model-android-en-us-0.3 model
 mono test.exe
 ```

README.ru.md

@@ -100,8 +100,8 @@ python3 setup.py install
 
 ```
 cd vosk-api/python/example
-wget https://github.com/alphacep/kaldi-android-demo/releases/download/2020-01/alphacep-model-android-en-us-0.3.tar.gz
-tar xf alphacep-model-android-en-us-0.3.tar.gz 
+wget https://alphacephei.com/kaldi/models/vosk-model-small-en-us-0.3.zip
+unzip alphacep-model-android-en-us-0.3.zip
 mv alphacep-model-android-en-us-0.3 model-en
 python3 ./test_simple.py test.wav
 ```
@@ -116,8 +116,8 @@ python3 ./test_simple.py test.wav
 
 ```
 cd java && KALDI_ROOT=<KALDI_ROOT> make
-wget https://github.com/alphacep/kaldi-android-demo/releases/download/2020-01/alphacep-model-android-en-us-0.3.tar.gz
-tar xf alphacep-model-android-en-us-0.3.tar.gz 
+wget https://alphacephei.com/kaldi/models/vosk-model-small-en-us-0.3.zip
+unzip alphacep-model-android-en-us-0.3.zip
 mv alphacep-model-android-en-us-0.3 model
 make run
 ```
@@ -128,8 +128,8 @@ make run
 
 ```
 cd csharp && KALDI_ROOT=<KALDI_ROOT> make
-wget https://github.com/alphacep/kaldi-android-demo/releases/download/2020-01/alphacep-model-android-en-us-0.3.tar.gz
-tar xf alphacep-model-android-en-us-0.3.tar.gz 
+wget https://alphacephei.com/kaldi/models/vosk-model-small-en-us-0.3.zip
+unzip alphacep-model-android-en-us-0.3.zip
 mv alphacep-model-android-en-us-0.3 model
 mono test.exe
 ```

android/CMakeLists.txt

@@ -45,6 +45,7 @@ target_link_libraries( kaldi_jni
              ${KALDI_ROOT}/src/tree/kaldi-tree.a
              ${KALDI_ROOT}/src/feat/kaldi-feat.a
              ${KALDI_ROOT}/src/lat/kaldi-lat.a
+             ${KALDI_ROOT}/src/lm/kaldi-lm.a
              ${KALDI_ROOT}/src/hmm/kaldi-hmm.a
              ${KALDI_ROOT}/src/transform/kaldi-transform.a
              ${KALDI_ROOT}/src/cudamatrix/kaldi-cudamatrix.a

android/src/main/java/org/kaldi/Assets.java

@@ -241,10 +241,6 @@ public class Assets {
             if (!items.get(path).equals(externalItems.get(path))
                     || !(new File(externalDir, path).exists()))
                 newItems.add(path);
-            else
-                Log.i(TAG,
-                        String.format("Skipping asset %s: checksums are equal", path));
-
         }
 
         unusedItems.addAll(externalItems.keySet());
@@ -252,13 +248,11 @@ public class Assets {
 
         for (String path : newItems) {
             File file = copy(path);
-            Log.i(TAG, String.format("Copying asset %s to %s", path, file));
         }
 
         for (String path : unusedItems) {
             File file = new File(externalDir, path);
             file.delete();
-            Log.i(TAG, String.format("Removing asset %s", file));
         }
 
         updateItemList(items);

android/src/main/java/org/kaldi/SpeechRecognizer.java

@@ -148,7 +148,6 @@ public class SpeechRecognizer {
     public boolean stop() {
         boolean result = stopRecognizerThread();
         if (result) {
-            Log.i(TAG, "Stop recognition");
             mainHandler.post(new ResultEvent(recognizer.Result(), true));
         }
         return result;
@@ -163,10 +162,6 @@ public class SpeechRecognizer {
     public boolean cancel() {
         boolean result = stopRecognizerThread();
         recognizer.Result(); // Reset recognizer state
-        if (result) {
-            Log.i(TAG, "Cancel recognition");
-        }
-
         return result;
     }
     
@@ -207,8 +202,6 @@ public class SpeechRecognizer {
                 return;
             }
 
-            Log.d(TAG, "Starting decoding");
-
             short[] buffer = new short[bufferSize];
 
             while (!interrupted()

csharp/Makefile

@@ -44,10 +44,10 @@ libkaldiwrap.so: $(VOSK_SOURCES)
 	$(CXX) -fpermissive $(CFLAGS) $(CPPFLAGS) -shared -o $@ $(VOSK_SOURCES) $(KALDI_LIBS)
 
 vosk_wrap.c: ../src/vosk.i
-	swig -csharp -DSWIG_CSHARP_NO_EXCEPTION_HELPER -dllimport "libkaldiwrap.so" \
+	swig -csharp -DSWIG_CSHARP_NO_EXCEPTION_HELPER -dllimport "libkaldiwrap" \
 	    -namespace "Kaldi" -outdir gen -o vosk_wrap.c ../src/vosk.i
 
-run:
+run: test.exe
 	mono test.exe
 
 clean:

csharp/test.cs

@@ -7,6 +7,7 @@ public class Test
    public static void Main()
    {
 
+        Vosk.SetLogLevel(0);
         Model model = new Model("model");
         KaldiRecognizer rec = new KaldiRecognizer(model, 16000.0f);
 

doc/models.md

@@ -4,72 +4,78 @@ This is the list of models compatible with Vosk-API.
 
 To add a new model here create an issue on Github.
 
-### English
-
 | Model                                                                                                     | Size  | Accuracy   | Notes                                                                                        |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [kaldi-en-us-aspire-0.1](http://alphacephei.com/kaldi/kaldi-en-us-aspire-0.1.tar.gz)                      |  363M |   TBD      | Trained on Fisher + more or less recent LM. Pretty outdated but still ok even even for calls |
-| [alphacep-model-android-en-us-0.3](http://alphacephei.com/kaldi/alphacep-model-android-en-us-0.3.tar.gz)  |  36M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
-
-### Chinese
-
-| Model                                                                                                     | Size  | Accuracy   | Notes                                                                                        |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [kaldi-cn-0.1.tar.gz](http://alphacephei.com/kaldi/kaldi-cn-0.1.tar.gz)                                   |  195M |   TBD      | Big narrowband Chinese model for server processing                                           |
-| [alphacep-model-android-cn-0.3](http://alphacephei.com/kaldi/alphacep-model-android-cn-0.3.tar.gz)        |  32M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
-
-### Russian
-
-| Model                                                                                                     | Size  | Accuracy   | Notes                                                                                        |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [kaldi-ru-0.10.tar.gz](http://alphacephei.com/kaldi/kaldi-ru-0.10.tar.gz)                                 |  2.5G |   TBD      | Big narrowband Russian model for server processing                                           |
-| [alphacep-model-android-ru-0.3](http://alphacephei.com/kaldi/alphacep-model-android-ru-0.3.tar.gz)        |  39M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
-
-### French
-
-| Model                                                                                                                   | Size  | Accuracy   | Notes                                                                                        |
 |-------------------------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [alphacep-model-android-fr-pguyot-0.3](http://alphacephei.com/kaldi/alphacep-model-android-fr-pguyot-0.3.tar.gz)        |  39M  |   TBD      | Lightweight wideband model for Android and RPi trained by [Paul Guyot](https://github.com/pguyot/zamia-speech/releases) |
-
-### German
-
-| Model                                                                                                     | Size  | Accuracy   | Notes                                                                                                |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|------------------------------------------------------------------------------------------------------|
-| [tuda-de](http://ltdata1.informatik.uni-hamburg.de/kaldi_tuda_de/de_400k_nnet3chain_tdnn1f_2048_sp_bi.tar.bz2)        |  566M |   TBD      | Wideband server model from [tuda-de](https://github.com/uhh-lt/kaldi-tuda-de)            |
-| [alphacep-model-android-de-zamia-0.3](http://alphacephei.com/kaldi/alphacep-model-android-de-zamia-0.3.tar.gz)        |  49M  |   TBD      | Lightweight wideband model for Android and RPi                                           |
-
-### Spanish
-
-| Model                                                                                                     | Size  | Accuracy   | Notes                                                                                        |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [alphacep-model-android-es-0.3](http://alphacephei.com/kaldi/alphacep-model-android-es-0.3.tar.gz)        |  33M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
-
-### Portuguese
-
-| Model                                                                                                     | Size  | Accuracy   | Notes                                                                                        |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [alphacep-model-android-pt-0.3](http://alphacephei.com/kaldi/alphacep-model-android-pt-0.3.tar.gz)        |  31M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
-
-### Dutch
-
-https://github.com/opensource-spraakherkenning-nl/Kaldi_NL
-
-### Greek
-
-| Model                                                                                                     | Size  | Accuracy   | Notes                                                                                        |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [kaldi-el-gr-0.6.tar.gz](http://alphacephei.com/kaldi/kaldi-el-gr-0.6.tar.gz)                             |  1.1G |   TBD      | Big narrowband Greek model for server processing, not extremely accurate though        |
+| **English**                                                                                               |       |            |  |
+| [vosk-model-en-us-aspire-0.2](http://alphacephei.com/kaldi/models/vosk-model-en-us-aspire-0.2.zip)        |  1.4G |   TBD      | Trained on Fisher + more or less recent LM. Should be pretty good for generic US English transcription |
+| [vosk-model-small-en-us-0.3](http://alphacephei.com/kaldi/models/vosk-model-small-en-us-0.3.zip)          |  36M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
+| **Chinese**                                                                                                   |       |            |  |
+| [vosk-model-cn-0.1.zip](http://alphacephei.com/kaldi/models/vosk-model-cn-0.1.zip)                        |  195M |   TBD      | Big narrowband Chinese model for server processing                                           |
+| [vosk-model-small-cn-0.3](http://alphacephei.com/kaldi/models/vosk-model-small-cn-0.3.zip)                |  32M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
+| **Russian**                                                                                                   |       |            |  |
+| [vosk-model-ru-0.10.zip](http://alphacephei.com/kaldi/models/vosk-model-ru-0.10.zip)                      |  2.5G |   TBD      | Big narrowband Russian model for server processing                                           |
+| [vosk-model-small-ru-0.4](http://alphacephei.com/kaldi/models/vosk-model-small-ru-0.4.zip)                |  39M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
+| **French**                                                                                                |       |            |  |
+| [vosk-model-small-fr-pguyot-0.3](http://alphacephei.com/kaldi/models/vosk-model-small-fr-pguyot-0.3.zip)                |  39M  |   TBD      | Lightweight wideband model for Android and RPi trained by [Paul Guyot](https://github.com/pguyot/zamia-speech/releases) |
+| **German**                                                                                                |       |            |  |
+| [tuda-de](http://ltdata1.informatik.uni-hamburg.de/kaldi_tuda_de/de_400k_nnet3chain_tdnn1f_2048_sp_bi.tar.bz2)    |  566M |   TBD      | Wideband server model from [tuda-de](https://github.com/uhh-lt/vosk-model-tuda-de)            |
+| [vosk-model-small-de-zamia-0.3](http://alphacephei.com/kaldi/models/vosk-model-small-de-zamia-0.3.zip)            |  49M  |   TBD      | Lightweight wideband model for Android and RPi                                           |
+| **Spanish**                                                                                                |       |            |  |
+| [vosk-model-small-es-0.3](http://alphacephei.com/kaldi/models/vosk-model-small-es-0.3.zip)                |  33M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
+| **Portuguese**                                                                                                |       |            |  |
+| [vosk-model-small-pt-0.3](http://alphacephei.com/kaldi/models/vosk-model-small-pt-0.3.zip)                |  31M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
+| **Greek**                                                                                                |       |            |  |
+| [vosk-model-el-gr-0.6.zip](http://alphacephei.com/kaldi/models/vosk-model-el-gr-0.6.zip)                  |  1.1G |   TBD      | Big narrowband Greek model for server processing, not extremely accurate though        |
+| **Turkish**                                                                                                |       |            |  |
+| [vosk-model-small-tr-0.3](http://alphacephei.com/kaldi/models/vosk-model-small-tr-0.3.zip)                |  35M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
+| **Vietnamese**                                                                                                |       |            |  |
+| [vosk-model-small-vn-0.3](http://alphacephei.com/kaldi/models/vosk-model-small-vn-0.3.zip)                |  32M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
+| **Speaker identification model**                                                                          |       |            |                                                                                              |
+| [vosk-model-spk-0.3](http://alphacephei.com/kaldi/models/vosk-model-spk-0.3.zip)                          |  13M  |   TBD      | Model for speaker identification, should work for all languages                              |
 
 
-### Turkish
+## Other models
 
-| Model                                                                                                     | Size  | Accuracy   | Notes                                                                                        |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [alphacep-model-android-tr-0.3](http://alphacephei.com/kaldi/alphacep-model-android-tr-0.3.tar.gz)        |  35M  |   TBD      | Lightweight wideband model for Android and RPi                                               |
+Other places where you can check for models which might be compatible:
 
+  * http://kaldi-asr.org/models.html - variety of models from Kaldi - librispeech, aspire, chinese models
+  * https://github.com/daanzu/kaldi-active-grammar/blob/master/docs/models.md - Big dictation models
+  * http://zamia-speech.org/asr/ - German and English model from Zamia
+  * https://github.com/pguyot/zamia-speech/releases - French models for Zamia
+  * https://github.com/opensource-spraakherkenning-nl/Kaldi_NL - Dutch model
+  * https://montreal-forced-aligner.readthedocs.io/en/latest/pretrained_models.html (GMM models, not compatible but might be still useful)
+  * https://github.com/goodatlas/zeroth - Korean Kaldi (just a recipe and data to train)
+  * https://github.com/undertheseanlp/automatic_speech_recognition - Vietnamese Kaldi project
 
-### Vietnamese
+## Training your own model
+
+You can train your model with Kaldi toolkit. The training is pretty standard - you need tdnn nnet3 model with ivectors. You can
+check mini_librispeech recipe for details. Some notes on training:
+
+  * For smaller mobile models watch number of parameters
+  * Train the model without pitch. It might be helpful for small amount of data, but for large database it doesn't give the advantage
+but complicates the processing and increases response time.
+  * Train ivector of dim 30 instead of standard 100 to save memory of mobile models.
+
+## Model structure
+
+Once you trained the model arrange the files according to the following layout (see en-us-aspire for details):
+
+  * `am/final.mdl` - acoustic model
+  * `conf/mfcc.conf` - mfcc config file. Make sure you take mfcc_hires.conf version if you are using hires model (most external ones)
+  * `conf/model.conf` - provide default decoding beams and silence phones. you have to create this file yourself, it is not present in kaldi model
+  * `ivector/final.dubm` - take ivector files from ivector extractor
+  * `ivector/final.ie`
+  * `ivector/final.mat`
+  * `ivector/splice.conf`
+  * `ivector/global_cmvn.stats`
+  * `ivector/online_cmvn.conf`
+  * `graph/phones/word_boundary.int` - from the graph
+  * `graph/HCLG.fst` - this is the decoding graph, if you are not using lookahead
+  * `graph/HCLr.fst` - use Gr.fst and HCLr.fst instead of one big HCLG.fst if you want to run rescoring
+  * `graph/Gr.fst`
+  * `graph/phones.txt` - from the graph
+  * `graph/words.txt` - from the graph
+  * `rescore/G.carpa` - carpa rescoring is optional but helpful in big models. Usually located inside data/lang_test_rescore
+  * `rescore/G.fst` - also optional if you want to use rescoring
 
-| Model                                                                                                     | Size  | Accuracy   | Notes                                                                                        |
-|-----------------------------------------------------------------------------------------------------------|-------|------------|----------------------------------------------------------------------------------------------|
-| [alphacep-model-android-vn-0.3](http://alphacephei.com/kaldi/alphacep-model-android-vn-0.3.tar.gz)        |  32M  |   TBD      | Lightweight wideband model for Android and RPi                                               |

java/Makefile

@@ -50,16 +50,16 @@ clean:
 	$(RM) *.so *_wrap.cc *_wrap.o test/*.class
 	$(RM) -r org model-en
 
-model-en:
-	wget https://github.com/alphacep/kaldi-android-demo/releases/download/2020-01/alphacep-model-android-en-us-0.3.tar.gz
-	tar xf alphacep-model-android-en-us-0.3.tar.gz && rm alphacep-model-android-en-us-0.3.tar.gz
-	mv alphacep-model-android-en-us-0.3 model-en
+model:
+	wget https://alphacephei.com/kaldi/models/vosk-model-small-en-us-0.3.zip
+	unzip vosk-model-small-en-us-0.3.zip && rm vosk-model-small-en-us-0.3.zip
+	mv vosk-model-small-en-us-0.3 model
 
 model-spk:
-	wget https://github.com/alphacep/kaldi-android-demo/releases/download/2020-01/alphacep-spk-model-0.3.tar.gz
-	tar xf alphacep-spk-model-0.3.tar.gz && rm alphacep-spk-model-0.3.tar.gz
-	mv alphacep-spk-model-0.3 model-spk
+	wget https://alphacephei.com/kaldi/models/vosk-model-spk-0.3.zip
+	unzip vosk-model-spk-0.3.zip && rm vosk-model-spk-0.3.zip
+	mv vosk-model-spk-0.3 model-spk
 
-run: model-en model-spk
+run: model model-spk
 	javac test/*.java org/kaldi/*.java
 	java -Djava.library.path=. -cp . test.DecoderTest

java/test/DecoderTest.java

@@ -11,6 +11,7 @@ import java.nio.*;
 import org.kaldi.KaldiRecognizer;
 import org.kaldi.Model;
 import org.kaldi.SpkModel;
+import org.kaldi.Vosk;
 
 public class DecoderTest {
     static {
@@ -18,6 +19,8 @@ public class DecoderTest {
     }
 
     public static void main(String args[]) throws IOException {
+        Vosk.SetLogLevel(-10);
+
         FileInputStream ais = new FileInputStream(new File("../python/example/test.wav"));
         Model model = new Model("model");
         SpkModel spkModel = new SpkModel("model-spk");

python/example/test_microphone.py

@@ -4,7 +4,7 @@ from vosk import Model, KaldiRecognizer
 import os
 
 if not os.path.exists("model"):
-    print ("Please download the model from https://github.com/alphacep/kaldi-android-demo/releases and unpack as 'model' in the current folder.")
+    print ("Please download the model from https://github.com/alphacep/vosk-api/blob/master/doc/models.md and unpack as 'model' in the current folder.")
     exit (1)
 
 import pyaudio
@@ -17,7 +17,7 @@ model = Model("model")
 rec = KaldiRecognizer(model, 16000)
 
 while True:
-    data = stream.read(2000)
+    data = stream.read(4000)
     if len(data) == 0:
         break
     if rec.AcceptWaveform(data):

python/example/test_simple.py

@@ -1,12 +1,14 @@
 #!/usr/bin/python3
 
-from vosk import Model, KaldiRecognizer
+from vosk import Model, KaldiRecognizer, SetLogLevel
 import sys
 import os
 import wave
 
+SetLogLevel(0)
+
 if not os.path.exists("model"):
-    print ("Please download the model from https://github.com/alphacep/kaldi-android-demo/releases and unpack as 'model' in the current folder.")
+    print ("Please download the model from https://github.com/alphacep/vosk-api/blob/master/doc/models.md and unpack as 'model' in the current folder.")
     exit (1)
 
 wf = wave.open(sys.argv[1], "rb")
@@ -18,7 +20,7 @@ model = Model("model")
 rec = KaldiRecognizer(model, wf.getframerate())
 
 while True:
-    data = wf.readframes(1000)
+    data = wf.readframes(4000)
     if len(data) == 0:
         break
     if rec.AcceptWaveform(data):

python/example/test_speaker.py

@@ -11,11 +11,11 @@ model_path = "model"
 spk_model_path = "model-spk"
 
 if not os.path.exists(model_path):
-    print ("Please download the model from https://github.com/alphacep/kaldi-android-demo/releases and unpack as {} in the current folder.".format(model_path))
+    print ("Please download the model from https://github.com/alphacep/vosk-api/blob/master/doc/models.md and unpack as {} in the current folder.".format(model_path))
     exit (1)
 
 if not os.path.exists(spk_model_path):
-    print ("Please download the speaker model from https://github.com/alphacep/kaldi-android-demo/releases and unpack as {} in the current folder.".format(spk_model_path))
+    print ("Please download the speaker model from https://github.com/alphacep/vosk-api/blob/master/doc/models.md and unpack as {} in the current folder.".format(spk_model_path))
     exit (1)
 
 wf = wave.open(sys.argv[1], "rb")
@@ -38,7 +38,7 @@ def cosine_dist(x, y):
     return 1 - np.dot(nx, ny) / np.linalg.norm(nx) / np.linalg.norm(ny)
 
 while True:
-    data = wf.readframes(1000)
+    data = wf.readframes(4000)
     if len(data) == 0:
         break
     if rec.AcceptWaveform(data):

python/example/test_text.py

@@ -6,7 +6,7 @@ import json
 import os
 
 if not os.path.exists("model"):
-    print ("Please download the model from https://github.com/alphacep/kaldi-android-demo/releases and unpack as 'model' in the current folder.")
+    print ("Please download the model from https://github.com/alphacep/vosk-api/blob/master/doc/models.md and unpack as 'model' in the current folder.")
     exit (1)
 
 
@@ -22,7 +22,7 @@ wf = open(sys.argv[1], "rb")
 wf.read(44) # skip header
 
 while True:
-    data = wf.read(2000)
+    data = wf.read(4000)
     if len(data) == 0:
         break
     if rec.AcceptWaveform(data):

python/example/test_words.py

@@ -6,7 +6,7 @@ import os
 import wave
 
 if not os.path.exists("model"):
-    print ("Please download the model from https://github.com/alphacep/kaldi-android-demo/releases and unpack as 'model' in the current folder.")
+    print ("Please download the model from https://github.com/alphacep/vosk-api/blob/master/doc/models.md and unpack as 'model' in the current folder.")
     exit (1)
 
 wf = wave.open(sys.argv[1], "rb")
@@ -19,7 +19,7 @@ model = Model("model")
 rec = KaldiRecognizer(model, wf.getframerate(), "zero oh one two three four five six seven eight nine")
 
 while True:
-    data = wf.readframes(1000)
+    data = wf.readframes(4000)
     if len(data) == 0:
         break
     if rec.AcceptWaveform(data):

python/setup.py

@@ -7,7 +7,7 @@ with open("README.md", "r") as fh:
 
 setuptools.setup(
     name="vosk", # Replace with your own username
-    version="0.3.6",
+    version="0.3.7",
     author="Alpha Cephei Inc",
     author_email="contact@alphacephei.com",
     description="API for Kaldi and Vosk",

python/vosk/__init__.py

@@ -1 +1,2 @@
-from .vosk import KaldiRecognizer, Model, SpkModel
+from .vosk import KaldiRecognizer, Model, SpkModel, SetLogLevel
+

src/model.cc

@@ -45,17 +45,79 @@ static FstRegisterer<NGramFst<StdArc>> NGramFst_StdArc_registerer;
 
 #ifdef __ANDROID__
 #include <android/log.h>
-static void AndroidLogHandler(const LogMessageEnvelope &env, const char *message)
+static void KaldiLogHandler(const LogMessageEnvelope &env, const char *message)
 {
-    __android_log_print(ANDROID_LOG_VERBOSE, "KaldiDemo", message, 1);
+  int priority;
+  if (env.severity > GetVerboseLevel())
+      return;
+
+  if (env.severity > LogMessageEnvelope::kInfo) {
+    priority = ANDROID_LOG_VERBOSE;
+  } else {
+    switch (env.severity) {
+    case LogMessageEnvelope::kInfo:
+      priority = ANDROID_LOG_INFO;
+      break;
+    case LogMessageEnvelope::kWarning:
+      priority = ANDROID_LOG_WARN;
+      break;
+    case LogMessageEnvelope::kAssertFailed:
+      priority = ANDROID_LOG_FATAL;
+      break;
+    case LogMessageEnvelope::kError:
+    default: // If not the ERROR, it still an error!
+      priority = ANDROID_LOG_ERROR;
+      break;
+    }
+  }
+
+  std::stringstream full_message;
+  full_message << env.func << "():" << env.file << ':'
+               << env.line << ") " << message;
+
+  __android_log_print(priority, "VoskAPI", "%s", full_message.str().c_str());
+}
+#else
+static void KaldiLogHandler(const LogMessageEnvelope &env, const char *message)
+{
+  if (env.severity > GetVerboseLevel())
+      return;
+
+  // Modified default Kaldi logging so we can disable LOG messages.
+  std::stringstream full_message;
+  if (env.severity > LogMessageEnvelope::kInfo) {
+    full_message << "VLOG[" << env.severity << "] (";
+  } else {
+    switch (env.severity) {
+    case LogMessageEnvelope::kInfo:
+      full_message << "LOG (";
+      break;
+    case LogMessageEnvelope::kWarning:
+      full_message << "WARNING (";
+      break;
+    case LogMessageEnvelope::kAssertFailed:
+      full_message << "ASSERTION_FAILED (";
+      break;
+    case LogMessageEnvelope::kError:
+    default: // If not the ERROR, it still an error!
+      full_message << "ERROR (";
+      break;
+    }
+  }
+  // Add other info from the envelope and the message text.
+  full_message << "VoskAPI" << ':'
+               << env.func << "():" << env.file << ':'
+               << env.line << ") " << message;
+
+  // Print the complete message to stderr.
+  full_message << "\n";
+  std::cerr << full_message.str();
 }
 #endif
 
 Model::Model(const char *model_path) : model_path_str_(model_path) {
 
-#ifdef __ANDROID__
-    SetLogHandler(AndroidLogHandler);
-#endif
+    SetLogHandler(KaldiLogHandler);
 
     struct stat buffer;
     string am_path = model_path_str_ + "/am/final.mdl";
@@ -87,6 +149,8 @@ void Model::ConfigureV1()
         "--endpoint.rule2.min-trailing-silence=0.5",
         "--endpoint.rule3.min-trailing-silence=1.0",
         "--endpoint.rule4.min-trailing-silence=2.0",
+
+        "--print-args=false",
     };
 
     kaldi::ParseOptions po("");

src/vosk.i

@@ -1,4 +1,8 @@
+#if SWIGPYTHON
 %module(package="vosk", "threads"=1) vosk
+#else
+%module Vosk
+#endif
 
 %include <typemaps.i>
 
@@ -113,3 +117,6 @@ typedef struct {} KaldiRecognizer;
         return vosk_recognizer_final_result($self);
     }
 }
+
+%rename(SetLogLevel) vosk_set_log_level;
+void vosk_set_log_level(int level);

src/vosk_api.cc

@@ -90,3 +90,8 @@ void vosk_recognizer_free(VoskRecognizer *recognizer)
 {
     delete (KaldiRecognizer *)(recognizer);
 }
+
+void vosk_set_log_level(int log_level)
+{
+    SetVerboseLevel(log_level);
+}

src/vosk_api.h

@@ -41,6 +41,14 @@ const char *vosk_recognizer_partial_result(VoskRecognizer *recognizer);
 const char *vosk_recognizer_final_result(VoskRecognizer *recognizer);
 void vosk_recognizer_free(VoskRecognizer *recognizer);
 
+/**
+ * Set log level for Kaldi messages
+ *   0 - default value to print info and error messages but no debug
+ *   less than 0 - don't print info messages
+ *   greather than 0 - more verbose mode
+ */
+void vosk_set_log_level(int log_level);
+
 #ifdef __cplusplus
 }
 #endif