No project description provided

These details have not been verified by PyPI

Project links

Homepage

Project description

Introduction

You can use sherpa-ncnn for real-time speech recognition (i.e., speech-to-text) on

Linux
macOS
Windows
Embedded Linux (32-bit arm and 64-bit aarch64)
Android
etc ...

We support all platforms that ncnn supports.

Everything can be compiled from source with static link. The generated executable depends only on system libraries.

HINT: It does not depend on PyTorch or any other inference frameworks other than ncnn.

Please see the documentation https://k2-fsa.github.io/sherpa/ncnn/index.html for installation and usages, e.g.,

How to build an Android app
How to download and use pre-trained models

We provide a few YouTube videos for demonstration about real-time speech recognition with sherpa-ncnn using a microphone:

English: https://www.bilibili.com/video/BV1TP411p7dh/
Chinese: https://www.bilibili.com/video/BV1214y177vu
Multilingual (Chinese + English) with endpointing Python demo : https://www.bilibili.com/video/BV1eK411y788/
Android demos
Multilingual (Chinese + English) Android demo 1: https://www.bilibili.com/video/BV1Ge411A7XS
Multilingual (Chinese + English) Android demo 2: https://www.bilibili.com/video/BV1eK411y788/
Chinese (with background noise) Android demo : https://www.bilibili.com/video/BV1GR4y167fx
Chinese Android demo : https://www.bilibili.com/video/BV1744y1Z76H
Chinese poem with background music Android demo : https://www.bilibili.com/video/BV1vR4y1k7eo

Project details

These details have not been verified by PyPI

Project links

Homepage

Release history Release notifications | RSS feed

2.1.10

Mar 9, 2024

2.1.9

Feb 24, 2024

2.1.8

Feb 23, 2024

2.1.7

Feb 6, 2024

2.1.6

Jan 12, 2024

2.1.5

Jan 12, 2024

2.1.4

Oct 17, 2023

2.1.3

Sep 19, 2023

2.1.2

Sep 5, 2023

2.1.1

Aug 31, 2023

2.1.0

Aug 31, 2023

2.0.7

Aug 18, 2023

2.0.6

Aug 18, 2023

2.0.5

Aug 4, 2023

2.0.2

May 24, 2023

2.0.1

May 20, 2023

2.0

May 19, 2023

This version

1.9.0

May 4, 2023

1.8.6

May 4, 2023

1.8.1

Apr 12, 2023

1.8.0

Mar 24, 2023

1.7.0

Mar 9, 2023

1.6.0

Mar 2, 2023

1.5.2

Feb 27, 2023

1.5.1

Feb 16, 2023

1.5.0

Feb 14, 2023

1.4.3

Feb 6, 2023

1.4.2

Feb 4, 2023

1.4.1

Feb 2, 2023

1.4.0

Feb 2, 2023

1.3.2

Jan 11, 2023

1.3.1

Jan 10, 2023

1.3

Jan 9, 2023

1.2

Jan 8, 2023

1.1

Dec 30, 2022

0.9.2

Dec 30, 2022

0.9.1

Dec 29, 2022

0.9

Dec 29, 2022

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

sherpa_ncnn-1.9.0-cp311-cp311-win_amd64.whl (3.3 MB view hashes)

Uploaded May 4, 2023 CPython 3.11 Windows x86-64

sherpa_ncnn-1.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.7 MB view hashes)

Uploaded May 4, 2023 CPython 3.11 manylinux: glibc 2.17+ x86-64

sherpa_ncnn-1.9.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl (2.5 MB view hashes)

Uploaded May 4, 2023 CPython 3.11 manylinux: glibc 2.17+ i686

sherpa_ncnn-1.9.0-cp311-cp311-macosx_10_9_x86_64.whl (3.0 MB view hashes)

Uploaded May 4, 2023 CPython 3.11 macOS 10.9+ x86-64

sherpa_ncnn-1.9.0-cp310-cp310-win_amd64.whl (3.3 MB view hashes)

Uploaded May 4, 2023 CPython 3.10 Windows x86-64

sherpa_ncnn-1.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.7 MB view hashes)

Uploaded May 4, 2023 CPython 3.10 manylinux: glibc 2.17+ x86-64

sherpa_ncnn-1.9.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl (2.5 MB view hashes)

Uploaded May 4, 2023 CPython 3.10 manylinux: glibc 2.17+ i686

sherpa_ncnn-1.9.0-cp310-cp310-macosx_10_9_x86_64.whl (3.0 MB view hashes)

Uploaded May 4, 2023 CPython 3.10 macOS 10.9+ x86-64

sherpa_ncnn-1.9.0-cp39-cp39-win_amd64.whl (3.3 MB view hashes)

Uploaded May 4, 2023 CPython 3.9 Windows x86-64

sherpa_ncnn-1.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.7 MB view hashes)

Uploaded May 4, 2023 CPython 3.9 manylinux: glibc 2.17+ x86-64

sherpa_ncnn-1.9.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl (2.5 MB view hashes)

Uploaded May 4, 2023 CPython 3.9 manylinux: glibc 2.17+ i686

sherpa_ncnn-1.9.0-cp39-cp39-macosx_10_9_x86_64.whl (3.0 MB view hashes)

Uploaded May 4, 2023 CPython 3.9 macOS 10.9+ x86-64

sherpa_ncnn-1.9.0-cp38-cp38-win_amd64.whl (3.3 MB view hashes)

Uploaded May 4, 2023 CPython 3.8 Windows x86-64

sherpa_ncnn-1.9.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.7 MB view hashes)

Uploaded May 4, 2023 CPython 3.8 manylinux: glibc 2.17+ x86-64

sherpa_ncnn-1.9.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl (2.5 MB view hashes)

Uploaded May 4, 2023 CPython 3.8 manylinux: glibc 2.17+ i686

sherpa_ncnn-1.9.0-cp38-cp38-macosx_10_9_x86_64.whl (3.0 MB view hashes)

Uploaded May 4, 2023 CPython 3.8 macOS 10.9+ x86-64

sherpa_ncnn-1.9.0-cp37-cp37m-win_amd64.whl (3.3 MB view hashes)

Uploaded May 4, 2023 CPython 3.7m Windows x86-64

sherpa_ncnn-1.9.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.7 MB view hashes)

Uploaded May 4, 2023 CPython 3.7m manylinux: glibc 2.17+ x86-64

sherpa_ncnn-1.9.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl (2.5 MB view hashes)

Uploaded May 4, 2023 CPython 3.7m manylinux: glibc 2.17+ i686

sherpa_ncnn-1.9.0-cp37-cp37m-macosx_10_9_x86_64.whl (3.0 MB view hashes)

Uploaded May 4, 2023 CPython 3.7m macOS 10.9+ x86-64

sherpa_ncnn-1.9.0-cp36-cp36m-win_amd64.whl (3.3 MB view hashes)

Uploaded May 4, 2023 CPython 3.6m Windows x86-64

sherpa_ncnn-1.9.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.7 MB view hashes)

Uploaded May 4, 2023 CPython 3.6m manylinux: glibc 2.17+ x86-64

sherpa_ncnn-1.9.0-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl (2.5 MB view hashes)

Uploaded May 4, 2023 CPython 3.6m manylinux: glibc 2.17+ i686

sherpa_ncnn-1.9.0-cp36-cp36m-macosx_10_9_x86_64.whl (3.0 MB view hashes)

Uploaded May 4, 2023 CPython 3.6m macOS 10.9+ x86-64

Hashes for sherpa_ncnn-1.9.0-cp311-cp311-win_amd64.whl

Hashes for sherpa_ncnn-1.9.0-cp311-cp311-win_amd64.whl
Algorithm	Hash digest
SHA256	`870b0a110b8f4dc495f50c1676ab19569186c1ea18a184e3ccbb0978ee14790a`
MD5	`43e5a83c376fef5897ab702df2e884ff`
BLAKE2b-256	`6a3353cf0c6c4fcb0d822afd3c906f3591a8207e50613eca289d73207bb24e53`

Hashes for sherpa_ncnn-1.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`28d184efa0cea770efed1bbf09c0cceba4fc63b2b83ce81f771765a98e286b76`
MD5	`3ab3d1db2d6f64fc1ee2a2b7545277a5`
BLAKE2b-256	`123efd4d1c4e1b0f8a18dc4e375314eb696067c55c3ede5438466a34deab0fcc`

Hashes for sherpa_ncnn-1.9.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl

Hashes for sherpa_ncnn-1.9.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm	Hash digest
SHA256	`65b916a57123e2a4de81d112943765526e4c140cb0e6cf019666f3b170620028`
MD5	`45bd206c14f71751e658056788056efa`
BLAKE2b-256	`ef0eeae1c40f0fbb8824530ecbfe63b76d35338e54b51ed9c8bfc5223e6bed54`

Hashes for sherpa_ncnn-1.9.0-cp311-cp311-macosx_10_9_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp311-cp311-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`ea4ed0c8ded9d5d433c0843ec33b5095ec7955f5b7eefe1fe864e107513031de`
MD5	`20998d1ff9c144ffc176e3ce377f4731`
BLAKE2b-256	`ec7382189a4cdde4fb4b465050b02d77c50ba3da42ac8e2bd7cc12aa42f3ed4f`

Hashes for sherpa_ncnn-1.9.0-cp310-cp310-win_amd64.whl

Hashes for sherpa_ncnn-1.9.0-cp310-cp310-win_amd64.whl
Algorithm	Hash digest
SHA256	`612c40e2d061b58b010b469b09c785482856a4480a1fb137595208dd8b5c97e0`
MD5	`ddbd12e8789947444c2bcc724dd45d6c`
BLAKE2b-256	`1ad3554a650efca19f18c105763799138df9711e624e1521536a6a0aaa0061aa`

Hashes for sherpa_ncnn-1.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`a75cd01787e56a3d2f7e5bf8eb51834597e51b4cf2f1e2d3905ab46e078f4511`
MD5	`843f3120e99562c0f1941974a3280182`
BLAKE2b-256	`e5ad8eb06b2ded9a25f3e7b7c42f36a74ec56a03f513f27e47a9e888ce14dd07`

Hashes for sherpa_ncnn-1.9.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl

Hashes for sherpa_ncnn-1.9.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm	Hash digest
SHA256	`bca42dbf66662aa4ad70d7d652d6ef9ecd2075841c00b1bde6ca0c7d7594c01b`
MD5	`b80585e8203af82ef9215f2c7ef2e62c`
BLAKE2b-256	`23151a4fa3f2e7c33b22c163c85c028501282ccb9d2e165c55e6a4d49260a168`

Hashes for sherpa_ncnn-1.9.0-cp310-cp310-macosx_10_9_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp310-cp310-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`0da51b21fc6a6a7c133ef4ee5fdf15f581a5fad2fffd327ac3765aa9897df373`
MD5	`af15ef0d2814789a043cc4e97dbdda81`
BLAKE2b-256	`3a650f4ba27b65251f08ed1e08e656eb48dbbddd4a9c5d6ef7e2714ea0d8ce2c`

Hashes for sherpa_ncnn-1.9.0-cp39-cp39-win_amd64.whl

Hashes for sherpa_ncnn-1.9.0-cp39-cp39-win_amd64.whl
Algorithm	Hash digest
SHA256	`3d33d84b426215468d78c789d165a75fae4ddf6c888edea00be6468ecf3d339a`
MD5	`a6dd4e5aa0a4aae92961a7d431b6ef06`
BLAKE2b-256	`3a8ee08062daa5395ab2dc0633bbba5605780b6895f8b3250d796b3d896c36d0`

Hashes for sherpa_ncnn-1.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`423f85b2ffe45269d4852d045bbe843b33b772e7bb1e8ee4df51386403bd517b`
MD5	`4e63b5ce3f886f14987e1502ad32900d`
BLAKE2b-256	`2183108e528fb98c316c63d6e613559536d59fb3c1d32903b9e035e7b73fe3c4`

Hashes for sherpa_ncnn-1.9.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl

Hashes for sherpa_ncnn-1.9.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm	Hash digest
SHA256	`1c1b2b4d4a6ce48091c7b3497f80ee4de975546a271f9339f4fb83d49214e33a`
MD5	`c9c959feca71d0220194f684d7c86f18`
BLAKE2b-256	`79fd10fd2032cd79f1a9ca26760fddec158508cb8e96ef87e9d679c71f96fd48`

Hashes for sherpa_ncnn-1.9.0-cp39-cp39-macosx_10_9_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp39-cp39-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`6d4f4d33a771ca7c4f469bd2464ae07a31515ad37fb9fe4a2c5eeaa4dbb4c7ed`
MD5	`3b67b21ea2b098dd91513f1ce5c868a0`
BLAKE2b-256	`1a6791210f05e240687974c5bc929cc0cdecb81cc7cbe62ae167c5e65ac7d474`

Hashes for sherpa_ncnn-1.9.0-cp38-cp38-win_amd64.whl

Hashes for sherpa_ncnn-1.9.0-cp38-cp38-win_amd64.whl
Algorithm	Hash digest
SHA256	`1571621c60aaf425f99b88d34f0692febbdd6579f89216d2aca88ed2b8f8332a`
MD5	`646e2c080ee32dfdb606d996d57e38be`
BLAKE2b-256	`49b05baa58875efa2fff2cafe1e71e948b2cc646abf1ae22980ec1e2cdf0348d`

Hashes for sherpa_ncnn-1.9.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`1b9ceecbcd84a22a9efed00a4ba1edc469083ff6a87ba98f080c9f017d21ee35`
MD5	`a590536bae5b74fea84f21324ee3f46b`
BLAKE2b-256	`57945cfe1c6c54b517c59d98d13d42a0b9372df094616c53e98e50ea655c153a`

Hashes for sherpa_ncnn-1.9.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl

Hashes for sherpa_ncnn-1.9.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm	Hash digest
SHA256	`311ffa741e6e77bddb597096a43594d2ff8702c7176ef5954168115a32a54fa2`
MD5	`572726bfc1dcf0487d56640431863575`
BLAKE2b-256	`2d207f5b703d46916512483581067b96aa6698a4f8f20429ddb01b6ffbb42ffe`

Hashes for sherpa_ncnn-1.9.0-cp38-cp38-macosx_10_9_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp38-cp38-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`4d0e3f453378f39a27bf9358c3102532b4d8b84e6885930df08d84b0aa551eae`
MD5	`3db800a301a3c33a0b47767107804747`
BLAKE2b-256	`0f6cadb0737d10ed2561db390b6a56d639ce62f179f732c3d6c34555251a4d45`

Hashes for sherpa_ncnn-1.9.0-cp37-cp37m-win_amd64.whl

Hashes for sherpa_ncnn-1.9.0-cp37-cp37m-win_amd64.whl
Algorithm	Hash digest
SHA256	`69f6223960c76d262952c37a610c6cfb8eb37c435eb30feafe2efe368515fc8c`
MD5	`2e621ee174fee2fc69a7766b13de43d2`
BLAKE2b-256	`5a4c966ff5b7362e072dee25c5cd427d57cd88e1e41861944d5ef1b50d0a10ea`

Hashes for sherpa_ncnn-1.9.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`45251a9255ea097ee09fc2c4747214754181218726cde93cb2e3e5433b72b6cf`
MD5	`a49c999b008d8b2e733cae3e4140ea00`
BLAKE2b-256	`b503fe729db7edf3d3bd7027d5d9dc2d3dbcbb9d0494a3c1e9e138a3fafce41f`

Hashes for sherpa_ncnn-1.9.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl

Hashes for sherpa_ncnn-1.9.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm	Hash digest
SHA256	`972fa1184dc768903c00da554a041e96a1ab76a57ccb8561e27764414c82765d`
MD5	`6dffb938de4711fae4bf1dee711d32e1`
BLAKE2b-256	`4d398635ba5f143935d5d7666c733fac7ac5ad741b9280e3a56a6410dcfd3c95`

Hashes for sherpa_ncnn-1.9.0-cp37-cp37m-macosx_10_9_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp37-cp37m-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`e24500493806ef8062b19514a1f30cb2396732e99b45872df791670c6ea136a2`
MD5	`dbcf01d6a471cdb0a7f384bda135e2b7`
BLAKE2b-256	`236da7d5fc8199b8194044edd6e11fb59b2628f14ac842512da26e8fd7a4fa95`

Hashes for sherpa_ncnn-1.9.0-cp36-cp36m-win_amd64.whl

Hashes for sherpa_ncnn-1.9.0-cp36-cp36m-win_amd64.whl
Algorithm	Hash digest
SHA256	`e6016ac12e1d90fc82baa8b89e0d92b8441400a967b974f0ba2458a97d8bdf35`
MD5	`6002f9a2b8791f4e041a3233e9d4c517`
BLAKE2b-256	`66dd64f8be6baaac4ae024abf74e5b591e32a2480c4ba8a9de02852a8e5de5de`

Hashes for sherpa_ncnn-1.9.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`9edc84f4f8a7dc69916345187bf46fbebe0f1f04bb478822113f13b6f42ccf40`
MD5	`d5895a8c6f1ab8de6d291a3663e643b1`
BLAKE2b-256	`4282191fca151981b012371d5d1a25d50f2dad18f0789117d988c3321bbb7fef`

Hashes for sherpa_ncnn-1.9.0-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl

Hashes for sherpa_ncnn-1.9.0-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm	Hash digest
SHA256	`6ee98131bc6599704e38c80e35a9502455d0ecc2d0f60c751bd9177de2dc3bcb`
MD5	`62cd24cd669b411555e57eeb5a29906b`
BLAKE2b-256	`f26071db9a9a5c25b73a17d80d2341e376cf99986c52584bd2e5423634307b72`

Hashes for sherpa_ncnn-1.9.0-cp36-cp36m-macosx_10_9_x86_64.whl

Hashes for sherpa_ncnn-1.9.0-cp36-cp36m-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`83eca396d1896555d371ebb2150770ff5199ac9d076d010204aa985cd91b16fe`
MD5	`c79201d7e336429a5152b8e1b61dc039`
BLAKE2b-256	`df3e82b7e89389531764b0cefe2cc9e395c1d0509bcf9d0dee465b0d834aa914`