Merge pull request #493 from snakers4/adamnsandle

Adamnsandle

.github/workflows/python-publish.yml

@@ -0,0 +1,40 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  push:
+    tags:        
+      - '*'   
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

README.md

@@ -25,6 +25,34 @@ https://user-images.githubusercontent.com/36505480/144874384-95f80f6d-a4f1-42cc-
 </details>
 
 <br/>
+
+<h2 align="center">Fast start</h2>
+<br/>
+
+**Using pip**:
+`pip install silero-vad`
+
+```python3
+from silero_vad import load_silero_vad, read_audio, get_speech_timestamps
+model = load_silero_vad()
+wav = read_audio('path_to_audio_file') # backend (sox, soundfile, or ffmpeg) required!
+speech_timestamps = get_speech_timestamps(wav, model)
+```
+
+**Using torch.hub**:
+```python3
+import torch
+torch.set_num_threads(1)
+
+model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad', model='silero_vad')
+(get_speech_timestamps, _, read_audio, _, _) = utils
+
+wav = read_audio('path_to_audio_file') # backend (sox, soundfile, or ffmpeg) required!
+speech_timestamps = get_speech_timestamps(wav, model)
+```
+
+<br/>
+
 <h2 align="center">Key Features</h2>
 <br/>
 
@@ -57,21 +85,7 @@ https://user-images.githubusercontent.com/36505480/144874384-95f80f6d-a4f1-42cc-
    Published under permissive license (MIT) Silero VAD has zero strings attached - no telemetry, no keys, no registration, no built-in expiration, no keys or vendor lock.
 
 <br/>
-<h2 align="center">Fast start</h2>
-<br/>
 
-```python3
-import torch
-torch.set_num_threads(1)
-
-model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad', model='silero_vad')
-(get_speech_timestamps, _, read_audio, _, _) = utils
-
-wav = read_audio('path_to_audio_file')
-speech_timestamps = get_speech_timestamps(wav, model)
-```
-
-<br/>
 <h2 align="center">Typical Use Cases</h2>
 <br/>
 
@@ -121,4 +135,6 @@ Please see our [wiki](https://github.com/snakers4/silero-models/wiki) for releva
 
 - Example of VAD ONNX Runtime model usage in [C++](https://github.com/snakers4/silero-vad/tree/master/examples/cpp) 
 
-- Voice activity detection for the [browser](https://github.com/ricky0123/vad) using ONNX Runtime Web 
+- Voice activity detection for the [browser](https://github.com/ricky0123/vad) using ONNX Runtime Web
+
+- [Rust](https://github.com/snakers4/silero-vad/tree/master/examples/rust-example), [Go](https://github.com/snakers4/silero-vad/tree/master/examples/go), [Java](https://github.com/snakers4/silero-vad/tree/master/examples/java-example) and [other](https://github.com/snakers4/silero-vad/tree/master/examples) examples

examples/cpp/silero-vad-onnx.cpp

@@ -120,8 +120,7 @@ private:
     void reset_states()
     {
         // Call reset before each audio start
-        std::memset(_h.data(), 0.0f, _h.size() * sizeof(float));
-        std::memset(_c.data(), 0.0f, _c.size() * sizeof(float));
+        std::memset(_state.data(), 0.0f, _state.size() * sizeof(float));
         triggered = false;
         temp_end = 0;
         current_sample = 0;
@@ -139,19 +138,16 @@ private:
         input.assign(data.begin(), data.end());
         Ort::Value input_ort = Ort::Value::CreateTensor<float>(
             memory_info, input.data(), input.size(), input_node_dims, 2);
+        Ort::Value state_ort = Ort::Value::CreateTensor<float>(
+            memory_info, _state.data(), _state.size(), state_node_dims, 3);
         Ort::Value sr_ort = Ort::Value::CreateTensor<int64_t>(
             memory_info, sr.data(), sr.size(), sr_node_dims, 1);
-        Ort::Value h_ort = Ort::Value::CreateTensor<float>(
-            memory_info, _h.data(), _h.size(), hc_node_dims, 3);
-        Ort::Value c_ort = Ort::Value::CreateTensor<float>(
-            memory_info, _c.data(), _c.size(), hc_node_dims, 3);
 
         // Clear and add inputs
         ort_inputs.clear();
         ort_inputs.emplace_back(std::move(input_ort));
+        ort_inputs.emplace_back(std::move(state_ort));
         ort_inputs.emplace_back(std::move(sr_ort));
-        ort_inputs.emplace_back(std::move(h_ort));
-        ort_inputs.emplace_back(std::move(c_ort));
 
         // Infer
         ort_outputs = session->Run(
@@ -161,10 +157,8 @@ private:
 
         // Output probability & update h,c recursively
         float speech_prob = ort_outputs[0].GetTensorMutableData<float>()[0];
-        float *hn = ort_outputs[1].GetTensorMutableData<float>();
-        std::memcpy(_h.data(), hn, size_hc * sizeof(float));
-        float *cn = ort_outputs[2].GetTensorMutableData<float>();
-        std::memcpy(_c.data(), cn, size_hc * sizeof(float));
+        float *stateN = ort_outputs[1].GetTensorMutableData<float>();
+        std::memcpy(_state.data(), stateN, size_state * sizeof(float));
 
         // Push forward sample index
         current_sample += window_size_samples;
@@ -376,27 +370,26 @@ private:
     // Inputs
     std::vector<Ort::Value> ort_inputs;
     
-    std::vector<const char *> input_node_names = {"input", "sr", "h", "c"};
+    std::vector<const char *> input_node_names = {"input", "state", "sr"};
     std::vector<float> input;
+    unsigned int size_state = 2 * 1 * 128; // It's FIXED.
+    std::vector<float> _state;
     std::vector<int64_t> sr;
-    unsigned int size_hc = 2 * 1 * 64; // It's FIXED.
-    std::vector<float> _h;
-    std::vector<float> _c;
 
-    int64_t input_node_dims[2] = {}; 
+    int64_t input_node_dims[2] = {};
+    const int64_t state_node_dims[3] = {2, 1, 128}; 
     const int64_t sr_node_dims[1] = {1};
-    const int64_t hc_node_dims[3] = {2, 1, 64};
 
     // Outputs
     std::vector<Ort::Value> ort_outputs;
-    std::vector<const char *> output_node_names = {"output", "hn", "cn"};
+    std::vector<const char *> output_node_names = {"output", "stateN"};
 
 public:
     // Construction
     VadIterator(const std::wstring ModelPath,
-        int Sample_rate = 16000, int windows_frame_size = 64,
+        int Sample_rate = 16000, int windows_frame_size = 32,
         float Threshold = 0.5, int min_silence_duration_ms = 0,
-        int speech_pad_ms = 64, int min_speech_duration_ms = 64,
+        int speech_pad_ms = 32, int min_speech_duration_ms = 32,
         float max_speech_duration_s = std::numeric_limits<float>::infinity())
     {
         init_onnx_model(ModelPath);
@@ -422,8 +415,7 @@ public:
         input_node_dims[0] = 1;
         input_node_dims[1] = window_size_samples;
 
-        _h.resize(size_hc);
-        _c.resize(size_hc);
+        _state.resize(size_state);
         sr.resize(1);
         sr[0] = sample_rate;
     };

examples/go/cmd/main.go

@@ -13,7 +13,6 @@ func main() {
 	sd, err := speech.NewDetector(speech.DetectorConfig{
 		ModelPath:            "../../files/silero_vad.onnx",
 		SampleRate:           16000,
-		WindowSize:           1536,
 		Threshold:            0.5,
 		MinSilenceDurationMs: 0,
 		SpeechPadMs:          0,
@@ -22,6 +21,10 @@ func main() {
 		log.Fatalf("failed to create speech detector: %s", err)
 	}
 
+	if len(os.Args) != 2 {
+		log.Fatalf("invalid arguments provided: expecting one file path")
+	}
+
 	f, err := os.Open(os.Args[1])
 	if err != nil {
 		log.Fatalf("failed to open sample audio file: %s", err)

examples/go/go.mod

@@ -4,7 +4,7 @@ go 1.21.4
 
 require (
 	github.com/go-audio/wav v1.1.0
-	github.com/streamer45/silero-vad-go v0.1.0
+	github.com/streamer45/silero-vad-go v0.2.0
 )
 
 require (

examples/go/go.sum

@@ -8,8 +8,8 @@ github.com/go-audio/wav v1.1.0 h1:jQgLtbqBzY7G+BM8fXF7AHUk1uHUviWS4X39d5rsL2g=
 github.com/go-audio/wav v1.1.0/go.mod h1:mpe9qfwbScEbkd8uybLuIpTgHyrISw/OTuvjUW2iGtE=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/streamer45/silero-vad-go v0.1.0 h1:0nGZ6VT3LKOkBG/w+4kljIB6brxtgQn6YuNjTVYjOQ4=
-github.com/streamer45/silero-vad-go v0.1.0/go.mod h1:B+2FXs/5fZ6pzl6unUZYhZqkYdOB+3saBVzjOzdZnUs=
+github.com/streamer45/silero-vad-go v0.2.0 h1:bbRTa6cQuc7VI88y0qicx375UyWoxE6wlVOF+mUg0+g=
+github.com/streamer45/silero-vad-go v0.2.0/go.mod h1:B+2FXs/5fZ6pzl6unUZYhZqkYdOB+3saBVzjOzdZnUs=
 github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

examples/microphone_and_webRTC_integration/microphone_and_webRTC_integration.py

@@ -186,7 +186,7 @@ if __name__ == '__main__':
                         help="same as trig_sum, but for switching from triggered to non-triggered state (non-speech)")
 
     parser.add_argument('-N', '--num_steps', type=int, default=8,
-                        help="nubmer of overlapping windows to split audio chunk into (we recommend 4 or 8)")
+                        help="number of overlapping windows to split audio chunk into (we recommend 4 or 8)")
 
     parser.add_argument('-nspw', '--num_samples_per_window', type=int, default=4000,
                         help="number of samples in each window, our models were trained using 4000 samples (250 ms) per window, so this is preferable value (lesser values reduce quality)")
@@ -198,4 +198,4 @@ if __name__ == '__main__':
                         help=" minimum silence duration in samples between to separate speech chunks")
     ARGS = parser.parse_args()
     ARGS.rate=DEFAULT_SAMPLE_RATE
-    main(ARGS)
+    main(ARGS)

files/lang_dict_95.json

@@ -1 +0,0 @@
-{"59": "mg, Malagasy", "76": "tk, Turkmen", "20": "lb, Luxembourgish, Letzeburgesch", "62": "or, Oriya", "30": "en, English", "26": "oc, Occitan", "69": "no, Norwegian", "77": "sr, Serbian", "90": "bs, Bosnian", "71": "el, Greek, Modern (1453\u2013)", "15": "az, Azerbaijani", "12": "lo, Lao", "85": "zh-HK, Chinese", "79": "cs, Czech", "43": "sv, Swedish", "37": "mn, Mongolian", "32": "fi, Finnish", "51": "tg, Tajik", "46": "am, Amharic", "17": "nn, Norwegian Nynorsk", "40": "ja, Japanese", "8": "it, Italian", "21": "ha, Hausa", "11": "as, Assamese", "29": "fa, Persian", "82": "bn, Bengali", "54": "mk, Macedonian", "31": "sw, Swahili", "45": "vi, Vietnamese", "41": "ur, Urdu", "74": "bo, Tibetan", "4": "hi, Hindi", "86": "mr, Marathi", "3": "fy-NL, Western Frisian", "65": "sk, Slovak", "2": "ln, Lingala", "92": "gl, Galician", "53": "sn, Shona", "87": "su, Sundanese", "35": "tt, Tatar", "93": "kn, Kannada", "6": "yo, Yoruba", "27": "ps, Pashto, Pushto", "34": "hy, Armenian", "25": "pa-IN, Punjabi, Panjabi", "23": "nl, Dutch, Flemish", "48": "th, Thai", "73": "mt, Maltese", "55": "ar, Arabic", "89": "ba, Bashkir", "78": "bg, Bulgarian", "42": "yi, Yiddish", "5": "ru, Russian", "84": "sv-SE, Swedish", "80": "tr, Turkish", "33": "sq, Albanian", "38": "kk, Kazakh", "50": "pl, Polish", "9": "hr, Croatian", "66": "ky, Kirghiz, Kyrgyz", "49": "hu, Hungarian", "10": "si, Sinhala, Sinhalese", "56": "la, Latin", "75": "de, German", "14": "ko, Korean", "22": "id, Indonesian", "47": "sl, Slovenian", "57": "be, Belarusian", "36": "ta, Tamil", "7": "da, Danish", "91": "sd, Sindhi", "28": "et, Estonian", "63": "pt, Portuguese", "60": "ne, Nepali", "94": "zh-TW, Chinese", "18": "zh-CN, Chinese", "88": "rw, Kinyarwanda", "19": "es, Spanish, Castilian", "39": "ht, Haitian, Haitian Creole", "64": "tl, Tagalog", "83": "ms, Malay", "70": "ro, Romanian, Moldavian, Moldovan", "68": "pa, Punjabi, Panjabi", "52": "uz, Uzbek", "58": "km, Central Khmer", "67": "my, Burmese", "0": "fr, French", "24": "af, Afrikaans", "16": "gu, Gujarati", "81": "so, Somali", "13": "uk, Ukrainian", "44": "ca, Catalan, Valencian", "72": "ml, Malayalam", "61": "te, Telugu", "1": "zh, Chinese"}

files/lang_group_dict_95.json

@@ -1 +0,0 @@
-{"0": ["Afrikaans", "Dutch, Flemish", "Western Frisian"], "1": ["Turkish", "Azerbaijani"], "2": ["Russian", "Slovak", "Ukrainian", "Czech", "Polish", "Belarusian"], "3": ["Bulgarian", "Macedonian", "Serbian", "Croatian", "Bosnian", "Slovenian"], "4": ["Norwegian Nynorsk", "Swedish", "Danish", "Norwegian"], "5": ["English"], "6": ["Finnish", "Estonian"], "7": ["Yiddish", "Luxembourgish, Letzeburgesch", "German"], "8": ["Spanish", "Occitan", "Portuguese", "Catalan, Valencian", "Galician", "Spanish, Castilian", "Italian"], "9": ["Maltese", "Arabic"], "10": ["Marathi"], "11": ["Hindi", "Urdu"], "12": ["Lao", "Thai"], "13": ["Malay", "Indonesian"], "14": ["Romanian, Moldavian, Moldovan"], "15": ["Tagalog"], "16": ["Tajik", "Persian"], "17": ["Kazakh", "Uzbek", "Kirghiz, Kyrgyz"], "18": ["Kinyarwanda"], "19": ["Tatar", "Bashkir"], "20": ["French"], "21": ["Chinese"], "22": ["Lingala"], "23": ["Yoruba"], "24": ["Sinhala, Sinhalese"], "25": ["Assamese"], "26": ["Korean"], "27": ["Gujarati"], "28": ["Hausa"], "29": ["Punjabi, Panjabi"], "30": ["Pashto, Pushto"], "31": ["Swahili"], "32": ["Albanian"], "33": ["Armenian"], "34": ["Mongolian"], "35": ["Tamil"], "36": ["Haitian, Haitian Creole"], "37": ["Japanese"], "38": ["Vietnamese"], "39": ["Amharic"], "40": ["Hungarian"], "41": ["Shona"], "42": ["Latin"], "43": ["Central Khmer"], "44": ["Malagasy"], "45": ["Nepali"], "46": ["Telugu"], "47": ["Oriya"], "48": ["Burmese"], "49": ["Greek, Modern (1453\u2013)"], "50": ["Malayalam"], "51": ["Tibetan"], "52": ["Turkmen"], "53": ["Somali"], "54": ["Bengali"], "55": ["Sundanese"], "56": ["Sindhi"], "57": ["Kannada"]}

hubconf.py

@@ -1,16 +1,15 @@
 dependencies = ['torch', 'torchaudio']
 import torch
-import json
 import os
-from utils_vad import (init_jit_model,
-                       get_speech_timestamps,
-                       save_audio,
-                       read_audio,
-                       VADIterator,
-                       collect_chunks,
-                       drop_chunks,
-                       Validator,
-                       OnnxWrapper)
+import sys
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'src'))
+from silero_vad.utils_vad import (init_jit_model,
+                                  get_speech_timestamps,
+                                  save_audio,
+                                  read_audio,
+                                  VADIterator,
+                                  collect_chunks,
+                                  OnnxWrapper)
 
 
 def versiontuple(v):
@@ -36,7 +35,7 @@ def silero_vad(onnx=False, force_onnx_cpu=False):
         if versiontuple(installed_version) < versiontuple(supported_version):
             raise Exception(f'Please install torch {supported_version} or greater ({installed_version} installed)')
 
-    model_dir = os.path.join(os.path.dirname(__file__), 'files')
+    model_dir = os.path.join(os.path.dirname(__file__), 'src', 'silero_vad', 'data')
     if onnx:
         model = OnnxWrapper(os.path.join(model_dir, 'silero_vad.onnx'), force_onnx_cpu)
     else:

pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+[project]
+name = "silero-vad"
+version = "5.1"
+authors = [
+  {name="Silero Team", email="hello@silero.ai"},
+]
+description = "Voice Activity Detector (VAD) by Silero"
+readme = "README.md"
+requires-python = ">=3.8"
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering",
+]
+dependencies = [
+  "torch>=1.12.0",
+  "torchaudio>=0.12.0",
+  "onnxruntime>=1.18.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/snakers4/silero-vad"
+Issues = "https://github.com/snakers4/silero-vad/issues"

silero-vad.ipynb

@@ -43,20 +43,30 @@
    },
    "outputs": [],
    "source": [
+    "USE_PIP = True # download model using pip package or torch.hub\n",
     "USE_ONNX = False # change this to True if you want to test onnx model\n",
     "if USE_ONNX:\n",
     "    !pip install -q onnxruntime\n",
+    "if USE_PIP:\n",
+    "  !pip install -q silero-vad\n",
+    "  from silero_vad import (load_silero_vad,\n",
+    "                          read_audio,\n",
+    "                          get_speech_timestamps,\n",
+    "                          save_audio,\n",
+    "                          VADIterator,\n",
+    "                          collect_chunks)\n",
+    "  model = load_silero_vad(onnx=USE_ONNX)\n",
+    "else:\n",
+    "  model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',\n",
+    "                                model='silero_vad',\n",
+    "                                force_reload=True,\n",
+    "                                onnx=USE_ONNX)\n",
     "\n",
-    "model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',\n",
-    "                              model='silero_vad',\n",
-    "                              force_reload=True,\n",
-    "                              onnx=USE_ONNX)\n",
-    "\n",
-    "(get_speech_timestamps,\n",
-    " save_audio,\n",
-    " read_audio,\n",
-    " VADIterator,\n",
-    " collect_chunks) = utils"
+    "  (get_speech_timestamps,\n",
+    "  save_audio,\n",
+    "  read_audio,\n",
+    "  VADIterator,\n",
+    "  collect_chunks) = utils"
    ]
   },
   {

src/silero_vad/__init__.py

@@ -0,0 +1,12 @@
+from importlib.metadata import version
+try:
+    __version__ = version(__name__)
+except:
+    pass
+
+from silero_vad.model import load_silero_vad
+from silero_vad.utils_vad import (get_speech_timestamps,
+                                  save_audio,
+                                  read_audio,
+                                  VADIterator,
+                                  collect_chunks)

src/silero_vad/model.py

@@ -0,0 +1,25 @@
+from .utils_vad import init_jit_model, OnnxWrapper
+import torch
+torch.set_num_threads(1)
+
+def load_silero_vad(onnx=False):
+    model_name = 'silero_vad.onnx' if onnx else 'silero_vad.jit'
+    package_path = "silero_vad.data"
+    
+    try:
+        import importlib_resources as impresources
+        model_file_path = str(impresources.files(package_path).joinpath(model_name))
+    except:
+        from importlib import resources as impresources
+        try:
+            with impresources.path(package_path, model_name) as f:
+                model_file_path = f
+        except:
+            model_file_path = str(impresources.files(package_path).joinpath(model_name))
+
+    if onnx:
+        model = OnnxWrapper(model_file_path, force_onnx_cpu=True)
+    else:
+        model = init_jit_model(model_file_path)
+    
+    return model

src/silero_vad/utils_vad.py

@@ -72,7 +72,7 @@ class OnnxWrapper():
 
         x = torch.cat([self._context, x], dim=1)
         if sr in [8000, 16000]:
-            ort_inputs = {'input': x.numpy(), 'state': self._state.numpy(), 'sr': np.array(sr)}
+            ort_inputs = {'input': x.numpy(), 'state': self._state.numpy(), 'sr': np.array(sr, dtype='int64')}
             ort_outs = self.session.run(None, ort_inputs)
             out, state = ort_outs
             self._state = torch.from_numpy(state)
@@ -132,18 +132,19 @@ class Validator():
 
 def read_audio(path: str,
                sampling_rate: int = 16000):
+    list_backends = torchaudio.list_audio_backends()
+    
+    assert len(list_backends) > 0, 'The list of available backends is empty, please install backend manually. \
+                                    \n Recommendations: \n \tSox (UNIX OS) \n \tSoundfile (Windows OS, UNIX OS) \n \tffmpeg (Windows OS, UNIX OS)'
 
-    sox_backends = set(['sox', 'sox_io'])
-    audio_backends = torchaudio.list_audio_backends()
-
-    if len(sox_backends.intersection(audio_backends)) > 0:
+    try:
         effects = [
             ['channels', '1'],
             ['rate', str(sampling_rate)]
         ]
 
         wav, sr = torchaudio.sox_effects.apply_effects_file(path, effects=effects)
-    else:
+    except:
         wav, sr = torchaudio.load(path)
 
         if wav.size(0) > 1: