Merge branch 'master' of github.com:snakers4/silero-vad

datasets/README.md

@@ -1,4 +1,7 @@
-# Готовая разметка внешних открытых наборов данных
+# Датасет Silero-VAD
+
+> Датасет создан при поддержке Фонда содействия инновациям в рамках федерального проекта «Искусственный
+интеллект» национальной программы «Цифровая экономика Российской Федерации».
 
 По ссылкам ниже представлены `.feather` файлы, содержащие размеченные с помощью Silero VAD открытые наборы аудиоданных, а также короткое описание каждого набора данных с примерами загрузки. `.feather` файлы можно открыть с помощью библиотеки `pandas`:
 ```python3
@@ -14,14 +17,14 @@ dataframe = pd.read_feather(PATH_TO_FEATHER_FILE)
 
 **Все данные размечены при временной дискретизации в ~30 миллисекунд (`num_samples` - 512)**
 
-| Название             | Число часов | Число языков | Ссылка | Лицензия |
+| Название             | Число часов | Число языков | Ссылка | Лицензия | md5sum |
-|----------------------|-------------|-------------|--------|----------|
+|----------------------|-------------|-------------|--------|----------|----------|
-| **Bible.is**             | 53138       | 1596        |    [URL](https://live.bible.is/)    |    [Уникальная](https://live.bible.is/terms)      |
+| **Bible.is**             | 53,138       | 1,596        |    [URL](https://live.bible.is/)    |    [Уникальная](https://live.bible.is/terms)      | ea404eeaf2cd283b8223f63002be11f9 |
-| **globalrecordings.net** | 9743        | 6171[^1]       |    [URL](https://globalrecordings.net/en)    |    CC BY-NC-SA 4.0      |
+| **globalrecordings.net** | 9,743        | 6,171[^1]       |    [URL](https://globalrecordings.net/en)    |    CC BY-NC-SA 4.0      | 3c5c0f31b0abd9fe94ddbe8b1e2eb326 |
-| **VoxLingua107**         | 6628        | 107         |    [URL](https://bark.phon.ioc.ee/voxlingua107/)    |     CC BY 4.0     |
+| **VoxLingua107**         | 6,628        | 107         |    [URL](https://bark.phon.ioc.ee/voxlingua107/)    |     CC BY 4.0     | 5dfef33b4d091b6d399cfaf3d05f2140 |
-| **Common Voice**         | 30329       | 120         |    [URL](https://commonvoice.mozilla.org/en/datasets)    |     CC0     |
+| **Common Voice**         | 30,329       | 120         |    [URL](https://commonvoice.mozilla.org/en/datasets)    |     CC0     | 5e30a85126adf74a5fd1496e6ac8695d |
-| **MLS**                  | 50709       | 8           |    [URL](https://www.openslr.org/94/)    |    CC BY 4.0      |
+| **MLS**                  | 50,709       | 8           |    [URL](https://www.openslr.org/94/)    |    CC BY 4.0      | a339d0e94bdf41bba3c003756254ac4e |
-| **Итого** | **150547** | **6171+** | | | |
+| **Итого**                  | **150,547**       | **6,171+**         |     |    |  |
 
 ## Bible.is
 
@@ -33,8 +36,8 @@ dataframe = pd.read_feather(PATH_TO_FEATHER_FILE)
 
 [Ссылка на `.feather` файл с разметкой](https://models.silero.ai/vad_datasets/globalrecordings.feather)
 
-- Колонка `folder_link` содержит ссылки на скачивание `.zip` архива для конкретного языка. Внимание! Ссылки на архивы дублируются, т.к каждый архив может содержать множество аудио;
+- Колонка `folder_link` содержит ссылки на скачивание `.zip` архива для конкретного языка. Внимание! Ссылки на архивы дублируются, т.к каждый архив может содержать множество аудио.
-- Колонка `audio_path` содержит пути до конкретного аудио после распаковки соответствующего архива из колонки `folder_link`.
+- Колонка `audio_path` содержит пути до конкретного аудио после распаковки соответствующего архива из колонки `folder_link`
 
 ``Количество уникальных ISO кодов данного датасета не совпадает с фактическим количеством представленных языков, т.к некоторые близкие языки могут кодироваться одним и тем же ISO кодом.``
 
@@ -42,8 +45,8 @@ dataframe = pd.read_feather(PATH_TO_FEATHER_FILE)
 
 [Ссылка на `.feather` файл с разметкой](https://models.silero.ai/vad_datasets/VoxLingua107.feather)
 
-- Колонка `folder_link` содержит ссылки на скачивание `.zip` архива для конкретного языка. Внимание! Ссылки на архивы дублируются, т.к каждый архив может содержать множество аудио;
+- Колонка `folder_link` содержит ссылки на скачивание `.zip` архива для конкретного языка. Внимание! Ссылки на архивы дублируются, т.к каждый архив может содержать множество аудио.
-- Колонка `audio_path` содержит пути до конкретного аудио после распаковки соответствующего архива из колонки `folder_link`.
+- Колонка `audio_path` содержит пути до конкретного аудио после распаковки соответствующего архива из колонки `folder_link`
 
 ## Common Voice
 
@@ -57,8 +60,25 @@ dataframe = pd.read_feather(PATH_TO_FEATHER_FILE)
 
 [Ссылка на `.feather` файл с разметкой](https://models.silero.ai/vad_datasets/MLS.feather)
 
-- Колонка `folder_link` содержит ссылки на скачивание `.zip` архива для конкретного языка. Внимание! Ссылки на архивы дублируются, т.к каждый архив может содержать множество аудио;
+- Колонка `folder_link` содержит ссылки на скачивание `.zip` архива для конкретного языка. Внимание! Ссылки на архивы дублируются, т.к каждый архив может содержать множество аудио.
-- Колонка `audio_path` содержит пути до конкретного аудио после распаковки соответствующего архива из колонки `folder_link`.
+- Колонка `audio_path` содержит пути до конкретного аудио после распаковки соответствующего архива из колонки `folder_link`
 
+## Лицензия
 
-[^1]: Количество уникальных ISO кодов данного датасета не совпадает с фактическим количеством представленных языков, т.к некоторые близкие языки могут кодироваться одним и тем же ISO кодом.
+Данный датасет распространяется под [лицензией](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en) `CC BY-NC-SA 4.0`.
+
+## Цитирование
+
+```
+@misc{Silero VAD Dataset,
+  author = {Silero Team},
+  title = {Silero-VAD Dataset: a large public Internet-scale dataset for voice activity detection for 6000+ languages},
+  year = {2024},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/snakers4/silero-vad/datasets/README.md}},
+  email = {hello@silero.ai}
+}
+```
+
+[^1]: ``Количество уникальных ISO кодов данного датасета не совпадает с фактическим количеством представленных языков, т.к некоторые близкие языки могут кодироваться одним и тем же ISO кодом.``

examples/rust-example/.gitignore

@@ -0,0 +1,2 @@
+target/
+recorder.wav

examples/rust-example/Cargo.lock

@@ -0,0 +1,781 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "adler"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
+
+[[package]]
+name = "autocfg"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c4b4d0bd25bd0b74681c0ad21497610ce1b7c91b1022cd21c80c6fbdd9476b0"
+
+[[package]]
+name = "base64"
+version = "0.22.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
+
+[[package]]
+name = "bitflags"
+version = "1.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
+
+[[package]]
+name = "bitflags"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf4b9d6a944f767f8e5e0db018570623c85f3d925ac718db4e06d0187adb21c1"
+
+[[package]]
+name = "block-buffer"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+dependencies = [
+ "generic-array",
+]
+
+[[package]]
+name = "bumpalo"
+version = "3.16.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
+
+[[package]]
+name = "cc"
+version = "1.0.98"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41c270e7540d725e65ac7f1b212ac8ce349719624d7bcff99f8e2e488e8cf03f"
+
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "cpufeatures"
+version = "0.2.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53fe5e26ff1b7aef8bca9c6080520cfb8d9333c7568e1829cef191a9723e5504"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "crc32fast"
+version = "1.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a97769d94ddab943e4510d138150169a2758b5ef3eb191a9ee688de3e23ef7b3"
+dependencies = [
+ "cfg-if",
+]
+
+[[package]]
+name = "crunchy"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a81dae078cea95a014a339291cec439d2f232ebe854a9d672b796c6afafa9b7"
+
+[[package]]
+name = "crypto-common"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1bfb12502f3fc46cca1bb51ac28df9d618d813cdc3d2f25b9fe775a34af26bb3"
+dependencies = [
+ "generic-array",
+ "typenum",
+]
+
+[[package]]
+name = "digest"
+version = "0.10.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+]
+
+[[package]]
+name = "errno"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "534c5cf6194dfab3db3242765c03bbe257cf92f22b38f6bc0c58d59108a820ba"
+dependencies = [
+ "libc",
+ "windows-sys",
+]
+
+[[package]]
+name = "filetime"
+version = "0.2.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1ee447700ac8aa0b2f2bd7bc4462ad686ba06baa6727ac149a2d6277f0d240fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "redox_syscall",
+ "windows-sys",
+]
+
+[[package]]
+name = "flate2"
+version = "1.0.30"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5f54427cfd1c7829e2a139fcefea601bf088ebca651d2bf53ebc600eac295dae"
+dependencies = [
+ "crc32fast",
+ "miniz_oxide",
+]
+
+[[package]]
+name = "form_urlencoded"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e13624c2627564efccf4934284bdd98cbaa14e79b0b5a141218e507b3a823456"
+dependencies = [
+ "percent-encoding",
+]
+
+[[package]]
+name = "generic-array"
+version = "0.14.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi",
+]
+
+[[package]]
+name = "half"
+version = "2.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6dd08c532ae367adf81c312a4580bc67f1d0fe8bc9c460520283f4c0ff277888"
+dependencies = [
+ "cfg-if",
+ "crunchy",
+]
+
+[[package]]
+name = "hound"
+version = "3.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "62adaabb884c94955b19907d60019f4e145d091c75345379e70d1ee696f7854f"
+
+[[package]]
+name = "idna"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "634d9b1461af396cad843f47fdba5597a4f9e6ddd4bfb6ff5d85028c25cb12f6"
+dependencies = [
+ "unicode-bidi",
+ "unicode-normalization",
+]
+
+[[package]]
+name = "js-sys"
+version = "0.3.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29c15563dc2726973df627357ce0c9ddddbea194836909d655df6a75d2cf296d"
+dependencies = [
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.155"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
+
+[[package]]
+name = "libloading"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c2a198fb6b0eada2a8df47933734e6d35d350665a33a3593d7164fa52c75c19"
+dependencies = [
+ "cfg-if",
+ "windows-targets",
+]
+
+[[package]]
+name = "linux-raw-sys"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89"
+
+[[package]]
+name = "log"
+version = "0.4.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
+
+[[package]]
+name = "matrixmultiply"
+version = "0.3.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7574c1cf36da4798ab73da5b215bbf444f50718207754cb522201d78d1cd0ff2"
+dependencies = [
+ "autocfg",
+ "rawpointer",
+]
+
+[[package]]
+name = "miniz_oxide"
+version = "0.7.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87dfd01fe195c66b572b37921ad8803d010623c0aca821bea2302239d155cdae"
+dependencies = [
+ "adler",
+]
+
+[[package]]
+name = "ndarray"
+version = "0.15.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "adb12d4e967ec485a5f71c6311fe28158e9d6f4bc4a447b474184d0f91a8fa32"
+dependencies = [
+ "matrixmultiply",
+ "num-complex",
+ "num-integer",
+ "num-traits",
+ "rawpointer",
+]
+
+[[package]]
+name = "num-complex"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-integer"
+version = "0.1.46"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
+
+[[package]]
+name = "ort"
+version = "2.0.0-rc.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0bc80894094c6a875bfac64415ed456fa661081a278a035e22be661305c87e14"
+dependencies = [
+ "half",
+ "js-sys",
+ "libloading",
+ "ndarray",
+ "ort-sys",
+ "thiserror",
+ "tracing",
+ "web-sys",
+]
+
+[[package]]
+name = "ort-sys"
+version = "2.0.0-rc.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b3d9c1373fc813d3f024d394f621f4c6dde0734c79b1c17113c3bb5bf0084bbe"
+dependencies = [
+ "flate2",
+ "sha2",
+ "tar",
+ "ureq",
+]
+
+[[package]]
+name = "percent-encoding"
+version = "2.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
+
+[[package]]
+name = "pin-project-lite"
+version = "0.2.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bda66fc9667c18cb2758a2ac84d1167245054bcf85d5d1aaa6923f45801bdd02"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.84"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec96c6a92621310b51366f1e28d05ef11489516e93be030060e5fc12024a49d6"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.36"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "rawpointer"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3"
+
+[[package]]
+name = "redox_syscall"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4722d768eff46b75989dd134e5c353f0d6296e5aaa3132e776cbdb56be7731aa"
+dependencies = [
+ "bitflags 1.3.2",
+]
+
+[[package]]
+name = "ring"
+version = "0.17.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c17fa4cb658e3583423e915b9f3acc01cceaee1860e33d59ebae66adc3a2dc0d"
+dependencies = [
+ "cc",
+ "cfg-if",
+ "getrandom",
+ "libc",
+ "spin",
+ "untrusted",
+ "windows-sys",
+]
+
+[[package]]
+name = "rust-example"
+version = "0.1.0"
+dependencies = [
+ "hound",
+ "ndarray",
+ "ort",
+]
+
+[[package]]
+name = "rustix"
+version = "0.38.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70dc5ec042f7a43c4a73241207cecc9873a06d45debb38b329f8541d85c2730f"
+dependencies = [
+ "bitflags 2.5.0",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys",
+]
+
+[[package]]
+name = "rustls"
+version = "0.22.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf4ef73721ac7bcd79b2b315da7779d8fc09718c6b3d2d1b2d94850eb8c18432"
+dependencies = [
+ "log",
+ "ring",
+ "rustls-pki-types",
+ "rustls-webpki",
+ "subtle",
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-pki-types"
+version = "1.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "976295e77ce332211c0d24d92c0e83e50f5c5f046d11082cea19f3df13a3562d"
+
+[[package]]
+name = "rustls-webpki"
+version = "0.102.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff448f7e92e913c4b7d4c6d8e4540a1724b319b4152b8aef6d4cf8339712b33e"
+dependencies = [
+ "ring",
+ "rustls-pki-types",
+ "untrusted",
+]
+
+[[package]]
+name = "sha2"
+version = "0.10.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "793db75ad2bcafc3ffa7c68b215fee268f537982cd901d132f89c6343f3a3dc8"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
+[[package]]
+name = "spin"
+version = "0.9.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6980e8d7511241f8acf4aebddbb1ff938df5eebe98691418c4468d0b72a96a67"
+
+[[package]]
+name = "subtle"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "81cdd64d312baedb58e21336b31bc043b77e01cc99033ce76ef539f78e965ebc"
+
+[[package]]
+name = "syn"
+version = "2.0.66"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c42f3f41a2de00b01c0aaad383c5a45241efc8b2d1eda5661812fda5f3cdcff5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "tar"
+version = "0.4.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b16afcea1f22891c49a00c751c7b63b2233284064f11a200fc624137c51e2ddb"
+dependencies = [
+ "filetime",
+ "libc",
+ "xattr",
+]
+
+[[package]]
+name = "thiserror"
+version = "1.0.61"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c546c80d6be4bc6a00c0f01730c08df82eaa7a7a61f11d656526506112cc1709"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.61"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "46c3384250002a6d5af4d114f2845d37b57521033f30d5c3f46c4d70e1197533"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "tinyvec"
+version = "1.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87cc5ceb3875bb20c2890005a4e226a4651264a5c75edb2421b52861a0a0cb50"
+dependencies = [
+ "tinyvec_macros",
+]
+
+[[package]]
+name = "tinyvec_macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
+
+[[package]]
+name = "tracing"
+version = "0.1.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c3523ab5a71916ccf420eebdf5521fcef02141234bbc0b8a49f2fdc4544364ef"
+dependencies = [
+ "pin-project-lite",
+ "tracing-attributes",
+ "tracing-core",
+]
+
+[[package]]
+name = "tracing-attributes"
+version = "0.1.27"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "tracing-core"
+version = "0.1.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c06d3da6113f116aaee68e4d601191614c9053067f9ab7f6edbcb161237daa54"
+dependencies = [
+ "once_cell",
+]
+
+[[package]]
+name = "typenum"
+version = "1.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825"
+
+[[package]]
+name = "unicode-bidi"
+version = "0.3.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08f95100a766bf4f8f28f90d77e0a5461bbdb219042e7679bebe79004fed8d75"
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
+
+[[package]]
+name = "unicode-normalization"
+version = "0.1.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a56d1686db2308d901306f92a263857ef59ea39678a5458e7cb17f01415101f5"
+dependencies = [
+ "tinyvec",
+]
+
+[[package]]
+name = "untrusted"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
+
+[[package]]
+name = "ureq"
+version = "2.9.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d11a831e3c0b56e438a28308e7c810799e3c118417f342d30ecec080105395cd"
+dependencies = [
+ "base64",
+ "log",
+ "once_cell",
+ "rustls",
+ "rustls-pki-types",
+ "rustls-webpki",
+ "url",
+ "webpki-roots",
+]
+
+[[package]]
+name = "url"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "31e6302e3bb753d46e83516cae55ae196fc0c309407cf11ab35cc51a4c2a4633"
+dependencies = [
+ "form_urlencoded",
+ "idna",
+ "percent-encoding",
+]
+
+[[package]]
+name = "version_check"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
+
+[[package]]
+name = "wasi"
+version = "0.11.0+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
+
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.92"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4be2531df63900aeb2bca0daaaddec08491ee64ceecbee5076636a3b026795a8"
+dependencies = [
+ "cfg-if",
+ "wasm-bindgen-macro",
+]
+
+[[package]]
+name = "wasm-bindgen-backend"
+version = "0.2.92"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "614d787b966d3989fa7bb98a654e369c762374fd3213d212cfc0251257e747da"
+dependencies = [
+ "bumpalo",
+ "log",
+ "once_cell",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.92"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1f8823de937b71b9460c0c34e25f3da88250760bec0ebac694b49997550d726"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.92"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-backend",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.92"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af190c94f2773fdb3729c55b007a722abb5384da03bc0986df4c289bf5567e96"
+
+[[package]]
+name = "web-sys"
+version = "0.3.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77afa9a11836342370f4817622a2f0f418b134426d91a82dfb48f532d2ec13ef"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "webpki-roots"
+version = "0.26.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b3de34ae270483955a94f4b21bdaaeb83d508bb84a01435f393818edb0012009"
+dependencies = [
+ "rustls-pki-types",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6f0713a46559409d202e70e28227288446bf7841d3211583a4b53e3f6d96e7eb"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7088eed71e8b8dda258ecc8bac5fb1153c5cffaf2578fc8ff5d61e23578d3263"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9985fd1504e250c615ca5f281c3f7a6da76213ebd5ccc9561496568a2752afb6"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "88ba073cf16d5372720ec942a8ccbf61626074c6d4dd2e745299726ce8b89670"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87f4261229030a858f36b459e748ae97545d6f1ec60e5e0d6a3d32e0dc232ee9"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "db3c2bf3d13d5b658be73463284eaf12830ac9a26a90c717b7f771dfe97487bf"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4e4246f76bdeff09eb48875a0fd3e2af6aada79d409d33011886d3e1581517d9"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "852298e482cd67c356ddd9570386e2862b5673c85bd5f88df9ab6802b334c596"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0"
+
+[[package]]
+name = "xattr"
+version = "1.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8da84f1a25939b27f6820d92aed108f83ff920fdf11a7b19366c27c4cda81d4f"
+dependencies = [
+ "libc",
+ "linux-raw-sys",
+ "rustix",
+]
+
+[[package]]
+name = "zeroize"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ced3678a2879b30306d323f4542626697a464a97c0a07c9aebf7ebca65cd4dde"

examples/rust-example/Cargo.toml

@@ -0,0 +1,9 @@
+[package]
+name = "rust-example"
+version = "0.1.0"
+edition = "2021"
+
+[dependencies]
+ort = { version = "2.0.0-rc.2", features = ["load-dynamic", "ndarray"] }
+ndarray = "0.15"
+hound = "3"

examples/rust-example/README.md

@@ -0,0 +1,19 @@
+# Stream example in Rust
+Made after [C++ stream example](https://github.com/snakers4/silero-vad/tree/master/examples/cpp)
+
+## Dependencies
+- To build Rust crate `ort` you need `cc` installed.
+
+## Usage
+Just
+```
+cargo run
+```
+If you run example outside of this repo adjust environment variable
+```
+SILERO_MODEL_PATH=/path/to/silero_vad.onnx cargo run 
+```
+If you need to test against other wav file, not `recorder.wav`, specify it as the first argument
+```
+cargo run -- /path/to/audio/file.wav
+```

examples/rust-example/src/main.rs

@@ -0,0 +1,36 @@
+mod silero;
+mod utils;
+mod vad_iter;
+
+fn main() {
+    let model_path = std::env::var("SILERO_MODEL_PATH")
+        .unwrap_or_else(|_| String::from("../../files/silero_vad.onnx"));
+    let audio_path = std::env::args()
+        .nth(1)
+        .unwrap_or_else(|| String::from("recorder.wav"));
+    let mut wav_reader = hound::WavReader::open(audio_path).unwrap();
+    let sample_rate = match wav_reader.spec().sample_rate {
+        8000 => utils::SampleRate::EightkHz,
+        16000 => utils::SampleRate::SixteenkHz,
+        _ => panic!("Unsupported sample rate. Expect 8 kHz or 16 kHz."),
+    };
+    if wav_reader.spec().sample_format != hound::SampleFormat::Int {
+        panic!("Unsupported sample format. Expect Int.");
+    }
+    let content = wav_reader
+        .samples()
+        .filter_map(|x| x.ok())
+        .collect::<Vec<i16>>();
+    assert!(!content.is_empty());
+    let silero = silero::Silero::new(sample_rate, model_path).unwrap();
+    let vad_params = utils::VadParams {
+        sample_rate: sample_rate.into(),
+        ..Default::default()
+    };
+    let mut vad_iterator = vad_iter::VadIter::new(silero, vad_params);
+    vad_iterator.process(&content).unwrap();
+    for timestamp in vad_iterator.speeches() {
+        println!("{}", timestamp);
+    }
+    println!("Finished.");
+}

examples/rust-example/src/silero.rs

@@ -0,0 +1,59 @@
+use crate::utils;
+use ndarray::{Array, Array2, ArrayBase, ArrayD, Dim, IxDynImpl, OwnedRepr};
+use std::path::Path;
+
+#[derive(Debug)]
+pub struct Silero {
+    session: ort::Session,
+    sample_rate: ArrayBase<OwnedRepr<i64>, Dim<[usize; 1]>>,
+    h: ArrayBase<OwnedRepr<f32>, Dim<IxDynImpl>>,
+    c: ArrayBase<OwnedRepr<f32>, Dim<IxDynImpl>>,
+}
+
+impl Silero {
+    pub fn new(
+        sample_rate: utils::SampleRate,
+        model_path: impl AsRef<Path>,
+    ) -> Result<Self, ort::Error> {
+        let session = ort::Session::builder()?.commit_from_file(model_path)?;
+        let h = ArrayD::<f32>::zeros([2, 1, 64].as_slice());
+        let c = ArrayD::<f32>::zeros([2, 1, 64].as_slice());
+        let sample_rate = Array::from_shape_vec([1], vec![sample_rate.into()]).unwrap();
+        Ok(Self {
+            session,
+            sample_rate,
+            h,
+            c,
+        })
+    }
+
+    pub fn reset(&mut self) {
+        self.h = ArrayD::<f32>::zeros([2, 1, 64].as_slice());
+        self.c = ArrayD::<f32>::zeros([2, 1, 64].as_slice());
+    }
+
+    pub fn calc_level(&mut self, audio_frame: &[i16]) -> Result<f32, ort::Error> {
+        let data = audio_frame
+            .iter()
+            .map(|x| (*x as f32) / (i16::MAX as f32))
+            .collect::<Vec<_>>();
+        let frame = Array2::<f32>::from_shape_vec([1, data.len()], data).unwrap();
+        let inps = ort::inputs![
+            frame,
+            self.sample_rate.clone(),
+            std::mem::take(&mut self.h),
+            std::mem::take(&mut self.c)
+        ]?;
+        let res = self
+            .session
+            .run(ort::SessionInputs::ValueSlice::<4>(&inps))?;
+        self.h = res["hn"].try_extract_tensor().unwrap().to_owned();
+        self.c = res["cn"].try_extract_tensor().unwrap().to_owned();
+        Ok(*res["output"]
+            .try_extract_raw_tensor::<f32>()
+            .unwrap()
+            .1
+            .first()
+            .unwrap())
+    }
+}

examples/rust-example/src/utils.rs

@@ -0,0 +1,60 @@
+#[derive(Debug, Clone, Copy)]
+pub enum SampleRate {
+    EightkHz,
+    SixteenkHz,
+}
+
+impl From<SampleRate> for i64 {
+    fn from(value: SampleRate) -> Self {
+        match value {
+            SampleRate::EightkHz => 8000,
+            SampleRate::SixteenkHz => 16000,
+        }
+    }
+}
+
+impl From<SampleRate> for usize {
+    fn from(value: SampleRate) -> Self {
+        match value {
+            SampleRate::EightkHz => 8000,
+            SampleRate::SixteenkHz => 16000,
+        }
+    }
+}
+
+#[derive(Debug)]
+pub struct VadParams {
+    pub frame_size: usize,
+    pub threshold: f32,
+    pub min_silence_duration_ms: usize,
+    pub speech_pad_ms: usize,
+    pub min_speech_duration_ms: usize,
+    pub max_speech_duration_s: f32,
+    pub sample_rate: usize,
+}
+
+impl Default for VadParams {
+    fn default() -> Self {
+        Self {
+            frame_size: 64,
+            threshold: 0.5,
+            min_silence_duration_ms: 0,
+            speech_pad_ms: 64,
+            min_speech_duration_ms: 64,
+            max_speech_duration_s: f32::INFINITY,
+            sample_rate: 16000,
+        }
+    }
+}
+
+#[derive(Debug, Default)]
+pub struct TimeStamp {
+    pub start: i64,
+    pub end: i64,
+}
+
+impl std::fmt::Display for TimeStamp {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        write!(f, "[start:{:08}, end:{:08}]", self.start, self.end)
+    }
+}

examples/rust-example/src/vad_iter.rs

@@ -0,0 +1,223 @@
+use crate::{silero, utils};
+
+const DEBUG_SPEECH_PROB: bool = true;
+#[derive(Debug)]
+pub struct VadIter {
+    silero: silero::Silero,
+    params: Params,
+    state: State,
+}
+
+impl VadIter {
+    pub fn new(silero: silero::Silero, params: utils::VadParams) -> Self {
+        Self {
+            silero,
+            params: Params::from(params),
+            state: State::new(),
+        }
+    }
+
+    pub fn process(&mut self, samples: &[i16]) -> Result<(), ort::Error> {
+        self.reset_states();
+        for audio_frame in samples.chunks_exact(self.params.frame_size_samples) {
+            let speech_prob = self.silero.calc_level(audio_frame)?;
+            self.state.update(&self.params, speech_prob);
+        }
+        self.state.check_for_last_speech(samples.len());
+        Ok(())
+    }
+
+    pub fn speeches(&self) -> &[utils::TimeStamp] {
+        &self.state.speeches
+    }
+}
+
+impl VadIter {
+    fn reset_states(&mut self) {
+        self.silero.reset();
+        self.state = State::new()
+    }
+}
+
+#[allow(unused)]
+#[derive(Debug)]
+struct Params {
+    frame_size: usize,
+    threshold: f32,
+    min_silence_duration_ms: usize,
+    speech_pad_ms: usize,
+    min_speech_duration_ms: usize,
+    max_speech_duration_s: f32,
+    sample_rate: usize,
+    sr_per_ms: usize,
+    frame_size_samples: usize,
+    min_speech_samples: usize,
+    speech_pad_samples: usize,
+    max_speech_samples: f32,
+    min_silence_samples: usize,
+    min_silence_samples_at_max_speech: usize,
+}
+
+impl From<utils::VadParams> for Params {
+    fn from(value: utils::VadParams) -> Self {
+        let frame_size = value.frame_size;
+        let threshold = value.threshold;
+        let min_silence_duration_ms = value.min_silence_duration_ms;
+        let speech_pad_ms = value.speech_pad_ms;
+        let min_speech_duration_ms = value.min_speech_duration_ms;
+        let max_speech_duration_s = value.max_speech_duration_s;
+        let sample_rate = value.sample_rate;
+        let sr_per_ms = sample_rate / 1000;
+        let frame_size_samples = frame_size * sr_per_ms;
+        let min_speech_samples = sr_per_ms * min_speech_duration_ms;
+        let speech_pad_samples = sr_per_ms * speech_pad_ms;
+        let max_speech_samples = sample_rate as f32 * max_speech_duration_s
+            - frame_size_samples as f32
+            - 2.0 * speech_pad_samples as f32;
+        let min_silence_samples = sr_per_ms * min_silence_duration_ms;
+        let min_silence_samples_at_max_speech = sr_per_ms * 98;
+        Self {
+            frame_size,
+            threshold,
+            min_silence_duration_ms,
+            speech_pad_ms,
+            min_speech_duration_ms,
+            max_speech_duration_s,
+            sample_rate,
+            sr_per_ms,
+            frame_size_samples,
+            min_speech_samples,
+            speech_pad_samples,
+            max_speech_samples,
+            min_silence_samples,
+            min_silence_samples_at_max_speech,
+        }
+    }
+}
+
+#[derive(Debug, Default)]
+struct State {
+    current_sample: usize,
+    temp_end: usize,
+    next_start: usize,
+    prev_end: usize,
+    triggered: bool,
+    current_speech: utils::TimeStamp,
+    speeches: Vec<utils::TimeStamp>,
+}
+
+impl State {
+    fn new() -> Self {
+        Default::default()
+    }
+
+    fn update(&mut self, params: &Params, speech_prob: f32) {
+        self.current_sample += params.frame_size_samples;
+        if speech_prob > params.threshold {
+            if self.temp_end != 0 {
+                self.temp_end = 0;
+                if self.next_start < self.prev_end {
+                    self.next_start = self
+                        .current_sample
+                        .saturating_sub(params.frame_size_samples)
+                }
+            }
+            if !self.triggered {
+                self.debug(speech_prob, params, "start");
+                self.triggered = true;
+                self.current_speech.start =
+                    self.current_sample as i64 - params.frame_size_samples as i64;
+            }
+            return;
+        }
+        if self.triggered
+            && (self.current_sample as i64 - self.current_speech.start) as f32
+                > params.max_speech_samples
+        {
+            if self.prev_end > 0 {
+                self.current_speech.end = self.prev_end as _;
+                self.take_speech();
+                if self.next_start < self.prev_end {
+                    self.triggered = false
+                } else {
+                    self.current_speech.start = self.next_start as _;
+                }
+                self.prev_end = 0;
+                self.next_start = 0;
+                self.temp_end = 0;
+            } else {
+                self.current_speech.end = self.current_sample as _;
+                self.take_speech();
+                self.prev_end = 0;
+                self.next_start = 0;
+                self.temp_end = 0;
+                self.triggered = false;
+            }
+            return;
+        }
+        if speech_prob >= (params.threshold - 0.15) && (speech_prob < params.threshold) {
+            if self.triggered {
+                self.debug(speech_prob, params, "speaking")
+            } else {
+                self.debug(speech_prob, params, "silence")
+            }
+        }
+        if self.triggered && speech_prob < (params.threshold - 0.15) {
+            self.debug(speech_prob, params, "end");
+            if self.temp_end == 0 {
+                self.temp_end = self.current_sample;
+            }
+            if self.current_sample.saturating_sub(self.temp_end)
+                > params.min_silence_samples_at_max_speech
+            {
+                self.prev_end = self.temp_end;
+            }
+            if self.current_sample.saturating_sub(self.temp_end) >= params.min_silence_samples {
+                self.current_speech.end = self.temp_end as _;
+                if self.current_speech.end - self.current_speech.start
+                    > params.min_speech_samples as _
+                {
+                    self.take_speech();
+                    self.prev_end = 0;
+                    self.next_start = 0;
+                    self.temp_end = 0;
+                    self.triggered = false;
+                }
+            }
+        }
+    }
+
+    fn take_speech(&mut self) {
+        self.speeches.push(std::mem::take(&mut self.current_speech)); // current speech becomes TimeStamp::default() due to take()
+    }
+
+    fn check_for_last_speech(&mut self, last_sample: usize) {
+        if self.current_speech.start > 0 {
+            self.current_speech.end = last_sample as _;
+            self.take_speech();
+            self.prev_end = 0;
+            self.next_start = 0;
+            self.temp_end = 0;
+            self.triggered = false;
+        }
+    }
+
+    fn debug(&self, speech_prob: f32, params: &Params, title: &str) {
+        if DEBUG_SPEECH_PROB {
+            let speech = self.current_sample as f32
+                - params.frame_size_samples as f32
+                - if title == "end" {
+                    params.speech_pad_samples
+                } else {
+                    0
+                } as f32; // minus window_size_samples to get precise start time point.
+            println!(
+                "[{:10}: {:.3} s ({:.3}) {:8}]",
+                title,
+                speech / params.sample_rate as f32,
+                speech_prob,
+                self.current_sample - params.frame_size_samples,
+            );
+        }
+    }
+}

utils_vad.py

@@ -156,7 +156,6 @@ def save_audio(path: str,
 
 def init_jit_model(model_path: str,
                    device=torch.device('cpu')):
-    torch.set_grad_enabled(False)
     model = torch.jit.load(model_path, map_location=device)
     model.eval()
     return model
@@ -172,6 +171,7 @@ def make_visualization(probs, step):
                  colormap='tab20')
 
 
+@torch.no_grad()
 def get_speech_timestamps(audio: torch.Tensor,
                           model,
                           threshold: float = 0.5,
@@ -484,6 +484,7 @@ class VADIterator:
         self.temp_end = 0
         self.current_sample = 0
 
+    @torch.no_grad()
     def __call__(self, x, return_seconds=False):
         """
         x: torch.Tensor