commit 6a8e9cfd4fb40ba304940f8a10d1c1bf60356711
Author: KeksNino <KeksNino@proton.me>
Date:   Wed Jul 29 03:23:08 2026 +0200

    Initial Commit

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..3a447bf
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+/target
+*.wav
diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..8902fcb
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,155 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "itoa"
+version = "1.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
+
+[[package]]
+name = "memchr"
+version = "2.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf8baf1c55e62ffcace7a9f06f4bd9cd3f0c4beb022d3b367256b91b87513d98"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.107"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "985e7ec9bb745e6ce6535b544d84d6cd6f7ad8bd711c398938ae983b91a766d9"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.47"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fbf4db142a473a8d80c26bbf18454ed458bf8d26c8219c331daecfdbd079001"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "serde"
+version = "1.0.229"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4148590afebada386688f18773da617792bf2ef03ffc1e4cbd2b1d45b023e0ba"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.229"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67dca2c9c51e58a4791a4b1ed58308b39c64224d349a935ab5039aa360942a48"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.229"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 3.0.3",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.151"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c841b55ecdae098c80dcae9cf767f6f8a0c2cdb3416bbef72181df4d0fe73f14"
+dependencies = [
+ "itoa",
+ "memchr",
+ "serde",
+ "serde_core",
+ "zmij",
+]
+
+[[package]]
+name = "speech-detection"
+version = "0.1.0"
+dependencies = [
+ "vosk",
+]
+
+[[package]]
+name = "syn"
+version = "2.0.119"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "syn"
+version = "3.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53e9bae58849f64dfa4f5d5ae372c8341f7305f82a3868709269343628b659a3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "thiserror"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+
+[[package]]
+name = "vosk"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae9e2a552b3fb49f097849cfed3d4a2a7163bb7ea507268666980605a676c627"
+dependencies = [
+ "serde",
+ "serde_json",
+ "thiserror",
+ "vosk-sys",
+]
+
+[[package]]
+name = "vosk-sys"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73ab2937e19c7d32c1a077a4a220011cbbb2b6ab83bb35635ffb65a82b7e43f6"
+
+[[package]]
+name = "zmij"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29666d0abbfad1e3dc4dcf6144730dd3a3ab225bbbdac83319345b1b44ccfc1b"
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..b0af471
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,7 @@
+[package]
+name = "speech-detection"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+vosk = "0.3.1"
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..c291f3e
--- /dev/null
+++ b/README.md
@@ -0,0 +1 @@
+Simple offline speech-detection to do voice commands
diff --git a/build.rs b/build.rs
new file mode 100644
index 0000000..0f417cb
--- /dev/null
+++ b/build.rs
@@ -0,0 +1,13 @@
+use std::{env, path::PathBuf};
+
+fn main() {
+    let root = PathBuf::from(env::var("CARGO_MANIFEST_DIR").unwrap());
+
+    println!(
+        "cargo:rustc-link-search=native={}",
+        root.join("vosk-linux-x86_64-0.3.45").display()
+    );
+    println!("cargo:rustc-link-lib=dylib=vosk");
+
+    println!("cargo:rerun-if-changed=vosk-linux-x86_64-0.3.45/vosk_api.h");
+}
diff --git a/flake.lock b/flake.lock
new file mode 100644
index 0000000..6e9867c
--- /dev/null
+++ b/flake.lock
@@ -0,0 +1,82 @@
+{
+  "nodes": {
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1785141334,
+        "narHash": "sha256-kh35kIx7el4Jk8Ki3BH9/Pn1eZYSYLJ6LMALos0zOy0=",
+        "owner": "nixos",
+        "repo": "nixpkgs",
+        "rev": "38a4887411571457d700c51c64a6e49ead2ed5ab",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nixos",
+        "ref": "nixpkgs-unstable",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "nixpkgs": "nixpkgs",
+        "rust-overlay": "rust-overlay",
+        "utils": "utils"
+      }
+    },
+    "rust-overlay": {
+      "inputs": {
+        "nixpkgs": [
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1785216007,
+        "narHash": "sha256-KrGilCiFVxEQOaBD3TODhklZzE7uICQvqsBWgycIABA=",
+        "owner": "oxalica",
+        "repo": "rust-overlay",
+        "rev": "8ec8a5a41f8d8244e672829c9cd705416139d3f0",
+        "type": "github"
+      },
+      "original": {
+        "owner": "oxalica",
+        "repo": "rust-overlay",
+        "type": "github"
+      }
+    },
+    "systems": {
+      "locked": {
+        "lastModified": 1681028828,
+        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-systems",
+        "repo": "default",
+        "type": "github"
+      }
+    },
+    "utils": {
+      "inputs": {
+        "systems": "systems"
+      },
+      "locked": {
+        "lastModified": 1731533236,
+        "narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "type": "github"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}
diff --git a/flake.nix b/flake.nix
new file mode 100644
index 0000000..4ac27ac
--- /dev/null
+++ b/flake.nix
@@ -0,0 +1,65 @@
+{
+  description = "Nix development flake for speech-detection";
+
+  inputs = {
+    nixpkgs.url = "github:nixos/nixpkgs?ref=nixpkgs-unstable";
+    utils.url = "github:numtide/flake-utils";
+    rust-overlay = {
+      url = "github:oxalica/rust-overlay";
+      inputs.nixpkgs.follows = "nixpkgs";
+    };
+  };
+
+  outputs =
+    {
+      self,
+      nixpkgs,
+      utils,
+      rust-overlay,
+      ...
+    }:
+
+    utils.lib.eachDefaultSystem (
+      system:
+      let
+        overlays = [ (import rust-overlay) ];
+        pkgs = import nixpkgs {
+          inherit system overlays;
+        };
+        rust = pkgs.rust-bin.fromRustupToolchainFile ./rust-toolchain.toml;
+
+        libPath =
+          with pkgs;
+          lib.makeLibraryPath [
+            gcc.cc.lib
+          ];
+
+      in
+      {
+        devShells = {
+          default =
+            with pkgs;
+            mkShell {
+              buildInputs = [
+                rust
+                cargo-nextest
+                fish
+                pkg-config
+                fontconfig
+                stdenv.cc.cc.lib
+              ];
+
+              env.RUST_SRC_PATH = "${pkgs.rust.packages.stable.rustPlatform.rustLibSrc}";
+              LD_LIBRARY_PATH = "$LD_LIBRARY_PATH:${libPath}";
+
+              shellHook = ''
+                echo Entered Rust dev shell for project speech-detection
+                export LIBC_PATH=${pkgs.stdenv.cc.cc.lib}/lib/
+                exec fish -C "set -ax LD_LIBRARY_PATH $PWD/vosk-linux-x86_64-0.3.45"
+              '';
+            };
+        };
+      }
+    );
+
+}
diff --git a/rust-toolchain.toml b/rust-toolchain.toml
new file mode 100644
index 0000000..e37dc8b
--- /dev/null
+++ b/rust-toolchain.toml
@@ -0,0 +1,9 @@
+[toolchain]
+channel = "nightly"
+components = [
+	"clippy",
+	"rustfmt",
+	"rust-analyzer",
+	"rust-src",
+	"rustc-codegen-cranelift",
+]
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..8056130
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,20 @@
+use vosk::{Model, Recognizer};
+
+fn main() {
+    let samples = [100, -2, 700, 30, 4, 5];
+    let model_path = "./vosk-model-small-en-us-0.15";
+
+    let model = Model::new(model_path).unwrap();
+    let mut recognizer = Recognizer::new(&model, 16000.0).unwrap();
+
+    recognizer.set_max_alternatives(10);
+    recognizer.set_words(true);
+    recognizer.set_partial_words(true);
+
+    for sample in samples.chunks(100) {
+        let _ = recognizer.accept_waveform(sample);
+        println!("{:#?}", recognizer.partial_result());
+    }
+
+    println!("{:#?}", recognizer.final_result().multiple().unwrap());
+}
diff --git a/vosk-linux-x86_64-0.3.45/libvosk.so b/vosk-linux-x86_64-0.3.45/libvosk.so
new file mode 100755
index 0000000..feb019f
Binary files /dev/null and b/vosk-linux-x86_64-0.3.45/libvosk.so differ
diff --git a/vosk-linux-x86_64-0.3.45/vosk_api.h b/vosk-linux-x86_64-0.3.45/vosk_api.h
new file mode 100644
index 0000000..9816019
--- /dev/null
+++ b/vosk-linux-x86_64-0.3.45/vosk_api.h
@@ -0,0 +1,361 @@
+// Copyright 2020-2021 Alpha Cephei Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//       http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+/* This header contains the C API for Vosk speech recognition system */
+
+#ifndef VOSK_API_H
+#define VOSK_API_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/** Model stores all the data required for recognition
+ *  it contains static data and can be shared across processing
+ *  threads. */
+typedef struct VoskModel VoskModel;
+
+
+/** Speaker model is the same as model but contains the data
+ *  for speaker identification. */
+typedef struct VoskSpkModel VoskSpkModel;
+
+
+/** Recognizer object is the main object which processes data.
+ *  Each recognizer usually runs in own thread and takes audio as input.
+ *  Once audio is processed recognizer returns JSON object as a string
+ *  which represent decoded information - words, confidences, times, n-best lists,
+ *  speaker information and so on */
+typedef struct VoskRecognizer VoskRecognizer;
+
+
+/**
+ * Batch model object
+ */
+typedef struct VoskBatchModel VoskBatchModel;
+
+/**
+ * Batch recognizer object
+ */
+typedef struct VoskBatchRecognizer VoskBatchRecognizer;
+
+
+/** Loads model data from the file and returns the model object
+ *
+ * @param model_path: the path of the model on the filesystem
+ * @returns model object or NULL if problem occured */
+VoskModel *vosk_model_new(const char *model_path);
+
+
+/** Releases the model memory
+ *
+ *  The model object is reference-counted so if some recognizer
+ *  depends on this model, model might still stay alive. When
+ *  last recognizer is released, model will be released too. */
+void vosk_model_free(VoskModel *model);
+
+
+/** Check if a word can be recognized by the model
+ * @param word: the word
+ * @returns the word symbol if @param word exists inside the model
+ * or -1 otherwise.
+ * Reminding that word symbol 0 is for <epsilon> */
+int vosk_model_find_word(VoskModel *model, const char *word);
+
+
+/** Loads speaker model data from the file and returns the model object
+ *
+ * @param model_path: the path of the model on the filesystem
+ * @returns model object or NULL if problem occured */
+VoskSpkModel *vosk_spk_model_new(const char *model_path);
+
+
+/** Releases the model memory
+ *
+ *  The model object is reference-counted so if some recognizer
+ *  depends on this model, model might still stay alive. When
+ *  last recognizer is released, model will be released too. */
+void vosk_spk_model_free(VoskSpkModel *model);
+
+/** Creates the recognizer object
+ *
+ *  The recognizers process the speech and return text using shared model data
+ *  @param model       VoskModel containing static data for recognizer. Model can be
+ *                     shared across recognizers, even running in different threads.
+ *  @param sample_rate The sample rate of the audio you going to feed into the recognizer.
+ *                     Make sure this rate matches the audio content, it is a common
+ *                     issue causing accuracy problems.
+ *  @returns recognizer object or NULL if problem occured */
+VoskRecognizer *vosk_recognizer_new(VoskModel *model, float sample_rate);
+
+
+/** Creates the recognizer object with speaker recognition
+ *
+ *  With the speaker recognition mode the recognizer not just recognize
+ *  text but also return speaker vectors one can use for speaker identification
+ *
+ *  @param model       VoskModel containing static data for recognizer. Model can be
+ *                     shared across recognizers, even running in different threads.
+ *  @param sample_rate The sample rate of the audio you going to feed into the recognizer.
+ *                     Make sure this rate matches the audio content, it is a common
+ *                     issue causing accuracy problems.
+ *  @param spk_model speaker model for speaker identification
+ *  @returns recognizer object or NULL if problem occured */
+VoskRecognizer *vosk_recognizer_new_spk(VoskModel *model, float sample_rate, VoskSpkModel *spk_model);
+
+
+/** Creates the recognizer object with the phrase list
+ *
+ *  Sometimes when you want to improve recognition accuracy and when you don't need
+ *  to recognize large vocabulary you can specify a list of phrases to recognize. This
+ *  will improve recognizer speed and accuracy but might return [unk] if user said
+ *  something different.
+ *
+ *  Only recognizers with lookahead models support this type of quick configuration.
+ *  Precompiled HCLG graph models are not supported.
+ *
+ *  @param model       VoskModel containing static data for recognizer. Model can be
+ *                     shared across recognizers, even running in different threads.
+ *  @param sample_rate The sample rate of the audio you going to feed into the recognizer.
+ *                     Make sure this rate matches the audio content, it is a common
+ *                     issue causing accuracy problems.
+ *  @param grammar The string with the list of phrases to recognize as JSON array of strings,
+ *                 for example "["one two three four five", "[unk]"]".
+ *
+ *  @returns recognizer object or NULL if problem occured */
+VoskRecognizer *vosk_recognizer_new_grm(VoskModel *model, float sample_rate, const char *grammar);
+
+
+/** Adds speaker model to already initialized recognizer
+ *
+ * Can add speaker recognition model to already created recognizer. Helps to initialize
+ * speaker recognition for grammar-based recognizer.
+ *
+ * @param spk_model Speaker recognition model */
+void vosk_recognizer_set_spk_model(VoskRecognizer *recognizer, VoskSpkModel *spk_model);
+
+
+/** Reconfigures recognizer to use grammar
+ *
+ * @param recognizer   Already running VoskRecognizer
+ * @param grammar      Set of phrases in JSON array of strings or "[]" to use default model graph.
+ *                     See also vosk_recognizer_new_grm
+ */
+void vosk_recognizer_set_grm(VoskRecognizer *recognizer, char const *grammar);
+
+
+/** Configures recognizer to output n-best results
+ *
+ * <pre>
+ *   {
+ *      "alternatives": [
+ *          { "text": "one two three four five", "confidence": 0.97 },
+ *          { "text": "one two three for five", "confidence": 0.03 },
+ *      ]
+ *   }
+ * </pre>
+ *
+ * @param max_alternatives - maximum alternatives to return from recognition results
+ */
+void vosk_recognizer_set_max_alternatives(VoskRecognizer *recognizer, int max_alternatives);
+
+
+/** Enables words with times in the output
+ *
+ * <pre>
+ *   "result" : [{
+ *       "conf" : 1.000000,
+ *       "end" : 1.110000,
+ *       "start" : 0.870000,
+ *       "word" : "what"
+ *     }, {
+ *       "conf" : 1.000000,
+ *       "end" : 1.530000,
+ *       "start" : 1.110000,
+ *       "word" : "zero"
+ *     }, {
+ *       "conf" : 1.000000,
+ *       "end" : 1.950000,
+ *       "start" : 1.530000,
+ *       "word" : "zero"
+ *     }, {
+ *       "conf" : 1.000000,
+ *       "end" : 2.340000,
+ *       "start" : 1.950000,
+ *       "word" : "zero"
+ *     }, {
+ *       "conf" : 1.000000,
+ *       "end" : 2.610000,
+ *       "start" : 2.340000,
+ *       "word" : "one"
+ *     }],
+ * </pre>
+ *
+ * @param words - boolean value
+ */
+void vosk_recognizer_set_words(VoskRecognizer *recognizer, int words);
+
+/** Like above return words and confidences in partial results
+ *
+ * @param partial_words - boolean value
+ */
+void vosk_recognizer_set_partial_words(VoskRecognizer *recognizer, int partial_words);
+
+/** Set NLSML output
+ * @param nlsml - boolean value
+ */
+void vosk_recognizer_set_nlsml(VoskRecognizer *recognizer, int nlsml);
+
+
+/** Accept voice data
+ *
+ *  accept and process new chunk of voice data
+ *
+ *  @param data - audio data in PCM 16-bit mono format
+ *  @param length - length of the audio data
+ *  @returns 1 if silence is occured and you can retrieve a new utterance with result method 
+ *           0 if decoding continues
+ *           -1 if exception occured */
+int vosk_recognizer_accept_waveform(VoskRecognizer *recognizer, const char *data, int length);
+
+
+/** Same as above but the version with the short data for language bindings where you have
+ *  audio as array of shorts */
+int vosk_recognizer_accept_waveform_s(VoskRecognizer *recognizer, const short *data, int length);
+
+
+/** Same as above but the version with the float data for language bindings where you have
+ *  audio as array of floats */
+int vosk_recognizer_accept_waveform_f(VoskRecognizer *recognizer, const float *data, int length);
+
+
+/** Returns speech recognition result
+ *
+ * @returns the result in JSON format which contains decoded line, decoded
+ *          words, times in seconds and confidences. You can parse this result
+ *          with any json parser
+ *
+ * <pre>
+ *  {
+ *    "text" : "what zero zero zero one"
+ *  }
+ * </pre>
+ *
+ * If alternatives enabled it returns result with alternatives, see also vosk_recognizer_set_max_alternatives().
+ *
+ * If word times enabled returns word time, see also vosk_recognizer_set_word_times().
+ */
+const char *vosk_recognizer_result(VoskRecognizer *recognizer);
+
+
+/** Returns partial speech recognition
+ *
+ * @returns partial speech recognition text which is not yet finalized.
+ *          result may change as recognizer process more data.
+ *
+ * <pre>
+ * {
+ *    "partial" : "cyril one eight zero"
+ * }
+ * </pre>
+ */
+const char *vosk_recognizer_partial_result(VoskRecognizer *recognizer);
+
+
+/** Returns speech recognition result. Same as result, but doesn't wait for silence
+ *  You usually call it in the end of the stream to get final bits of audio. It
+ *  flushes the feature pipeline, so all remaining audio chunks got processed.
+ *
+ *  @returns speech result in JSON format.
+ */
+const char *vosk_recognizer_final_result(VoskRecognizer *recognizer);
+
+
+/** Resets the recognizer
+ *
+ *  Resets current results so the recognition can continue from scratch */
+void vosk_recognizer_reset(VoskRecognizer *recognizer);
+
+
+/** Releases recognizer object
+ *
+ *  Underlying model is also unreferenced and if needed released */
+void vosk_recognizer_free(VoskRecognizer *recognizer);
+
+/** Set log level for Kaldi messages
+ *
+ *  @param log_level the level
+ *     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);
+
+/**
+ *  Init, automatically select a CUDA device and allow multithreading.
+ *  Must be called once from the main thread.
+ *  Has no effect if HAVE_CUDA flag is not set.
+ */
+void vosk_gpu_init();
+
+/**
+ *  Init CUDA device in a multi-threaded environment.
+ *  Must be called for each thread.
+ *  Has no effect if HAVE_CUDA flag is not set.
+ */
+void vosk_gpu_thread_init();
+
+/** Creates the batch recognizer object
+ *
+ *  @returns model object or NULL if problem occured */
+VoskBatchModel *vosk_batch_model_new(const char *model_path);
+
+/** Releases batch model object */
+void vosk_batch_model_free(VoskBatchModel *model);
+
+/** Wait for the processing */
+void vosk_batch_model_wait(VoskBatchModel *model);
+
+/** Creates batch recognizer object
+ *  @returns recognizer object or NULL if problem occured */
+VoskBatchRecognizer *vosk_batch_recognizer_new(VoskBatchModel *model, float sample_rate);
+ 
+/** Releases batch recognizer object */
+void vosk_batch_recognizer_free(VoskBatchRecognizer *recognizer);
+
+/** Accept batch voice data */
+void vosk_batch_recognizer_accept_waveform(VoskBatchRecognizer *recognizer, const char *data, int length);
+
+/** Set NLSML output
+ * @param nlsml - boolean value
+ */
+void vosk_batch_recognizer_set_nlsml(VoskBatchRecognizer *recognizer, int nlsml);
+
+/** Closes the stream */
+void vosk_batch_recognizer_finish_stream(VoskBatchRecognizer *recognizer);
+
+/** Return results */
+const char *vosk_batch_recognizer_front_result(VoskBatchRecognizer *recognizer);
+
+/** Release and free first retrieved result */
+void vosk_batch_recognizer_pop(VoskBatchRecognizer *recognizer);
+
+/** Get amount of pending chunks for more intelligent waiting */
+int vosk_batch_recognizer_get_pending_chunks(VoskBatchRecognizer *recognizer);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* VOSK_API_H */
diff --git a/vosk-model-small-en-us-0.15/README b/vosk-model-small-en-us-0.15/README
new file mode 100644
index 0000000..a7f7931
--- /dev/null
+++ b/vosk-model-small-en-us-0.15/README
@@ -0,0 +1,9 @@
+US English model for mobile Vosk applications
+
+Copyright 2020 Alpha Cephei Inc
+
+Accuracy: 10.38 (tedlium test) 9.85 (librispeech test-clean)
+Speed: 0.11xRT (desktop)
+Latency: 0.15s (right context)
+
+
diff --git a/vosk-model-small-en-us-0.15/am/final.mdl b/vosk-model-small-en-us-0.15/am/final.mdl
new file mode 100644
index 0000000..5596b31
Binary files /dev/null and b/vosk-model-small-en-us-0.15/am/final.mdl differ
diff --git a/vosk-model-small-en-us-0.15/conf/mfcc.conf b/vosk-model-small-en-us-0.15/conf/mfcc.conf
new file mode 100644
index 0000000..eaa40c5
--- /dev/null
+++ b/vosk-model-small-en-us-0.15/conf/mfcc.conf
@@ -0,0 +1,7 @@
+--sample-frequency=16000
+--use-energy=false
+--num-mel-bins=40
+--num-ceps=40
+--low-freq=20
+--high-freq=7600
+--allow-downsample=true
diff --git a/vosk-model-small-en-us-0.15/conf/model.conf b/vosk-model-small-en-us-0.15/conf/model.conf
new file mode 100644
index 0000000..9d5b0da
--- /dev/null
+++ b/vosk-model-small-en-us-0.15/conf/model.conf
@@ -0,0 +1,10 @@
+--min-active=200
+--max-active=3000
+--beam=10.0
+--lattice-beam=2.0
+--acoustic-scale=1.0
+--frame-subsampling-factor=3
+--endpoint.silence-phones=1:2:3:4:5:6:7:8:9:10
+--endpoint.rule2.min-trailing-silence=0.5
+--endpoint.rule3.min-trailing-silence=0.75
+--endpoint.rule4.min-trailing-silence=1.0
diff --git a/vosk-model-small-en-us-0.15/graph/Gr.fst b/vosk-model-small-en-us-0.15/graph/Gr.fst
new file mode 100644
index 0000000..1f292e6
Binary files /dev/null and b/vosk-model-small-en-us-0.15/graph/Gr.fst differ
diff --git a/vosk-model-small-en-us-0.15/graph/HCLr.fst b/vosk-model-small-en-us-0.15/graph/HCLr.fst
new file mode 100644
index 0000000..9797b26
Binary files /dev/null and b/vosk-model-small-en-us-0.15/graph/HCLr.fst differ
diff --git a/vosk-model-small-en-us-0.15/graph/disambig_tid.int b/vosk-model-small-en-us-0.15/graph/disambig_tid.int
new file mode 100644
index 0000000..762fd5f
--- /dev/null
+++ b/vosk-model-small-en-us-0.15/graph/disambig_tid.int
@@ -0,0 +1,17 @@
+10015
+10016
+10017
+10018
+10019
+10020
+10021
+10022
+10023
+10024
+10025
+10026
+10027
+10028
+10029
+10030
+10031
diff --git a/vosk-model-small-en-us-0.15/graph/phones/word_boundary.int b/vosk-model-small-en-us-0.15/graph/phones/word_boundary.int
new file mode 100644
index 0000000..df23fd7
--- /dev/null
+++ b/vosk-model-small-en-us-0.15/graph/phones/word_boundary.int
@@ -0,0 +1,166 @@
+1 nonword
+2 begin
+3 end
+4 internal
+5 singleton
+6 nonword
+7 begin
+8 end
+9 internal
+10 singleton
+11 begin
+12 end
+13 internal
+14 singleton
+15 begin
+16 end
+17 internal
+18 singleton
+19 begin
+20 end
+21 internal
+22 singleton
+23 begin
+24 end
+25 internal
+26 singleton
+27 begin
+28 end
+29 internal
+30 singleton
+31 begin
+32 end
+33 internal
+34 singleton
+35 begin
+36 end
+37 internal
+38 singleton
+39 begin
+40 end
+41 internal
+42 singleton
+43 begin
+44 end
+45 internal
+46 singleton
+47 begin
+48 end
+49 internal
+50 singleton
+51 begin
+52 end
+53 internal
+54 singleton
+55 begin
+56 end
+57 internal
+58 singleton
+59 begin
+60 end
+61 internal
+62 singleton
+63 begin
+64 end
+65 internal
+66 singleton
+67 begin
+68 end
+69 internal
+70 singleton
+71 begin
+72 end
+73 internal
+74 singleton
+75 begin
+76 end
+77 internal
+78 singleton
+79 begin
+80 end
+81 internal
+82 singleton
+83 begin
+84 end
+85 internal
+86 singleton
+87 begin
+88 end
+89 internal
+90 singleton
+91 begin
+92 end
+93 internal
+94 singleton
+95 begin
+96 end
+97 internal
+98 singleton
+99 begin
+100 end
+101 internal
+102 singleton
+103 begin
+104 end
+105 internal
+106 singleton
+107 begin
+108 end
+109 internal
+110 singleton
+111 begin
+112 end
+113 internal
+114 singleton
+115 begin
+116 end
+117 internal
+118 singleton
+119 begin
+120 end
+121 internal
+122 singleton
+123 begin
+124 end
+125 internal
+126 singleton
+127 begin
+128 end
+129 internal
+130 singleton
+131 begin
+132 end
+133 internal
+134 singleton
+135 begin
+136 end
+137 internal
+138 singleton
+139 begin
+140 end
+141 internal
+142 singleton
+143 begin
+144 end
+145 internal
+146 singleton
+147 begin
+148 end
+149 internal
+150 singleton
+151 begin
+152 end
+153 internal
+154 singleton
+155 begin
+156 end
+157 internal
+158 singleton
+159 begin
+160 end
+161 internal
+162 singleton
+163 begin
+164 end
+165 internal
+166 singleton
diff --git a/vosk-model-small-en-us-0.15/ivector/final.dubm b/vosk-model-small-en-us-0.15/ivector/final.dubm
new file mode 100644
index 0000000..db789eb
Binary files /dev/null and b/vosk-model-small-en-us-0.15/ivector/final.dubm differ
diff --git a/vosk-model-small-en-us-0.15/ivector/final.ie b/vosk-model-small-en-us-0.15/ivector/final.ie
new file mode 100644
index 0000000..93737bf
Binary files /dev/null and b/vosk-model-small-en-us-0.15/ivector/final.ie differ
diff --git a/vosk-model-small-en-us-0.15/ivector/final.mat b/vosk-model-small-en-us-0.15/ivector/final.mat
new file mode 100644
index 0000000..c3ec635
Binary files /dev/null and b/vosk-model-small-en-us-0.15/ivector/final.mat differ
diff --git a/vosk-model-small-en-us-0.15/ivector/global_cmvn.stats b/vosk-model-small-en-us-0.15/ivector/global_cmvn.stats
new file mode 100644
index 0000000..b9d92ef
--- /dev/null
+++ b/vosk-model-small-en-us-0.15/ivector/global_cmvn.stats
@@ -0,0 +1,3 @@
+ [
+  1.682383e+11 -1.1595e+10 -1.521733e+10 4.32034e+09 -2.257938e+10 -1.969666e+10 -2.559265e+10 -1.535687e+10 -1.276854e+10 -4.494483e+09 -1.209085e+10 -5.64008e+09 -1.134847e+10 -3.419512e+09 -1.079542e+10 -4.145463e+09 -6.637486e+09 -1.11318e+09 -3.479773e+09 -1.245932e+08 -1.386961e+09 6.560655e+07 -2.436518e+08 -4.032432e+07 4.620046e+08 -7.714964e+07 9.551484e+08 -4.119761e+08 8.208582e+08 -7.117156e+08 7.457703e+08 -4.3106e+08 1.202726e+09 2.904036e+08 1.231931e+09 3.629848e+08 6.366939e+08 -4.586172e+08 -5.267629e+08 -3.507819e+08 1.679838e+09 
+  1.741141e+13 8.92488e+11 8.743834e+11 8.848896e+11 1.190313e+12 1.160279e+12 1.300066e+12 1.005678e+12 9.39335e+11 8.089614e+11 7.927041e+11 6.882427e+11 6.444235e+11 5.151451e+11 4.825723e+11 3.210106e+11 2.720254e+11 1.772539e+11 1.248102e+11 6.691599e+10 3.599804e+10 1.207574e+10 1.679301e+09 4.594778e+08 5.821614e+09 1.451758e+10 2.55803e+10 3.43277e+10 4.245286e+10 4.784859e+10 4.988591e+10 4.925451e+10 5.074584e+10 4.9557e+10 4.407876e+10 3.421443e+10 3.138606e+10 2.539716e+10 1.948134e+10 1.381167e+10 0 ]
diff --git a/vosk-model-small-en-us-0.15/ivector/online_cmvn.conf b/vosk-model-small-en-us-0.15/ivector/online_cmvn.conf
new file mode 100644
index 0000000..7748a4a
--- /dev/null
+++ b/vosk-model-small-en-us-0.15/ivector/online_cmvn.conf
@@ -0,0 +1 @@
+# configuration file for apply-cmvn-online, used in the script ../local/run_online_decoding.sh
diff --git a/vosk-model-small-en-us-0.15/ivector/splice.conf b/vosk-model-small-en-us-0.15/ivector/splice.conf
new file mode 100644
index 0000000..960cd2e
--- /dev/null
+++ b/vosk-model-small-en-us-0.15/ivector/splice.conf
@@ -0,0 +1,2 @@
+--left-context=3
+--right-context=3