Skip to main content

FastASR

Project description

FastASR

这是一个用C++实现ASR推理的项目,它依赖很少,安装也很简单,推理速度很快,在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来,数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时), 所以识别效果也很好,可以媲美许多商用的ASR软件。

项目简介

目前本项目实现了4个模型,3个非流式模型,1个流式模型,如下表所示。

名称 来源 数据集 模型 语言
paraformer 阿里达摩院 私有数据集(60000h) Paraformer-large zh+en
k2_rnnt2 kaldi2 WenetSpeech(10000h) pruned_transducer_stateless2 zh
conformer paddlespeech WenetSpeech(10000h) conformer_wenetspeech-zh-16k zh
conformer_online paddlespeech WenetSpeech(10000h) conformer_online_wenetspeech-zh-16k zh
  • 非流式模型:每次识别是以句子为单位,所以实时性会差一些,但准确率会高一些。
  • 流式模型:模型的输入是语音流,并实时返回语音识别的结果,但是准确率会下降些。

conformer_online是流式模型,其它模型为非流式模型。 目前通过使用VAD技术, 非流式模型支持大段的长语音识别。

上面提到的这些模型都是基于深度学习框架(paddlepaddle或pytorch)实现的, 本身的性能已经很不错了,即使在没有GPU的个人电脑上运行, 也能满足实时性的要求(如:时长为10s的语音,推理时间小于10s,即可满足实时性)。

但是要把深度学习模型部署在ARM平台,会遇到两个方面的困难。

  • 不容易安装,需要自己编译一些组件。
  • 执行效率很慢,无法满足实时性的要求。

因此就有这个项目,它由纯C++编写,仅实现了模型的推理过程。

  • 语言优势: 由于C++和Python不同,是编译型语言,编译器会根据编译选项针对不同平台的CPU进行优化,更适合在不同CPU平台上面部署,充分利用CPU的计算资源。
  • 独立: 实现不依赖于现有的深度学习框架如pytorch、paddle、tensorflow等。
  • 依赖少: 项目仅使用了两个第三方库libfftw3和libopenblas,并无其他依赖,所以在各个平台的可移植行很好,通用性很强。
  • 效率高:算法中大量使用指针,减少原有算法中reshape和permute的操作,减少不必要的数据拷贝,从而提升算法性能。

针对C++用户和python用户,本项目分别生成了静态库libfastasr.a和PyFastASR.XXX模块,调用方法可以参考example目录中的例子。

未完成工作

  • 量化和压缩模型

python安装

目前fastasr在个平台的支持情况如下表, 其他未支持的平台可通过源码编译获得对应的whl包。

macOS Intel Windows 64bit Windows 32bit Linux x86 Linux x64 Linux aarch64
CPython 3.6
CPython 3.7
CPython 3.8
CPython 3.9
CPython 3.10
CPython 3.11

可通过pip直接安装

pip install fastasr

源码编译安装指南

Ubuntu 安装依赖

安装依赖库libfftw3

sudo apt-get install libfftw3-dev libfftw3-single3

安装依赖库libopenblas

sudo apt-get install libopenblas-dev

安装python环境

sudo apt-get install python3 python3-dev

MacOS 安装依赖

安装依赖库fftw

sudo brew install fftw

安装依赖库openblas

sudo brew install openblas

编译源码

Build for Linux

下载最新版的源码

git clone https://github.com/chenkui164/FastASR.git

编译最新版的源码,

cd FastASR/
mkdir build
cd build
cmake -DCMAKE_BUILD_TYPE=Release ..
make

编译python的whl安装包

cd FastASR/
python -m build

Build for Windows

Windows编译指南

使用VisualStudio 2022打开CMakeLists.txt,选择Release编译。 需要在vs2022安装linux开发组件。

下载预训练模型

paraformer预训练模型下载

进入FastASR/models/paraformer_cli文件夹,用于存放下载的预训练模型.

cd ../models/paraformer_cli

从modelscope官网下载预训练模型,预训练模型所在的仓库地址 也可通过命令一键下载。

wget --user-agent="Mozilla/5.0" -c "https://www.modelscope.cn/api/v1/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/repo?Revision=v1.0.4&FilePath=model.pb"

mv repo\?Revision\=v1.0.4\&FilePath\=model.pb model.pb 

将用于Python的模型转换为C++的,这样更方便通过内存映射的方式直接读取参数,加快模型读取速度。

../scripts/paraformer_convert.py model.pb

查看转换后的参数文件wenet_params.bin的md5码,md5码为c77bc27e5758ebdc28a9024460e48602,表示转换正确。

md5sum -b wenet_params.bin

k2_rnnt2预训练模型下载

进入FastASR/models/k2_rnnt2_cli文件夹,用于存放下载的预训练模型.

cd ../models/k2_rnnt2_cli

从huggingface官网下载预训练模型,预训练模型所在的仓库地址 也可通过命令一键下载。

wget -c https://huggingface.co/luomingshuang/icefall_asr_wenetspeech_pruned_transducer_stateless2/resolve/main/exp/pretrained_epoch_10_avg_2.pt

将用于Python的模型转换为C++的,这样更方便通过内存映射的方式直接读取参数,加快模型读取速度。

../scripts/k2_rnnt2_convert.py pretrained_epoch_10_avg_2.pt

查看转换后的参数文件wenet_params.bin的md5码,md5码为33a941f3c1a20a5adfb6f18006c11513,表示转换正确。

md5sum -b wenet_params.bin

conformer_wenetspeech-zh-16k预训练模型下载

进入FastASR/models/paddlespeech_cli文件夹,用于存放下载的预训练模型.

cd ../models/paddlespeech_cli

从PaddleSpeech官网下载预训练模型,如果之前已经在运行过PaddleSpeech, 则可以不用下载,它已经在目录~/.paddlespeech/models/conformer_wenetspeech-zh-16k中。

wget -c https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar.gz

将压缩包解压wenetspeech目录下

mkdir wenetspeech
tar -xzvf asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar.gz -C wenetspeech

将用于Python的模型转换为C++的,这样更方便通过内存映射的方式直接读取参数,加快模型读取速度。

../scripts/paddlespeech_convert.py wenetspeech/exp/conformer/checkpoints/wenetspeech.pdparams

查看转换后的参数文件wenet_params.bin的md5码,md5码为9cfcf11ee70cb9423528b1f66a87eafd,表示转换正确。

md5sum -b wenet_params.bin

流模式预训练模型下载

进入FastASR/models/paddlespeech_stream文件夹,用于存放下载的预训练模型.

cd ../models/paddlespeech_stream

从PaddleSpeech官网下载预训练模型,如果之前已经在运行过PaddleSpeech, 则可以不用下载,它已经在目录~/.paddlespeech/models/conformer_online_wenetspeech-zh-16k中。

wget -c https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar.gz

将压缩包解压wenetspeech目录下

mkdir wenetspeech
tar -xzvf asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar.gz -C wenetspeech

将用于Python的模型转换为C++的,这样更方便通过内存映射的方式直接读取参数,加快模型读取速度。

../scripts/paddlespeech_convert.py wenetspeech/exp/chunk_conformer/checkpoints/avg_10.pdparams

查看转换后的参数文件wenet_params.bin的md5码,md5码为367a285d43442ecfd9c9e5f5e1145b84,表示转换正确。

md5sum -b wenet_params.bin

测试例子

进入项目的根目录FastASR下载用于测试的wav文件

下载时长为5S的测试音频

wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav 

下载时长为30min的测试音频

wget -c https://github.com/chenkui164/FastASR/releases/download/V0.01/long.wav

paraformer模型测试

第一个参数为预训练模型存放的目录;
第二个参数为需要识别的语音文件。

./build/examples/paraformer_cli models/paraformer_cli/ zh.wav

程序输出

Audio time is 4.996812 s. len is 79949
Model initialization takes 0.319781s.
Result: "我认为跑步最重要的就是给我带来了身体健康".
Model inference takes 0.695871s.

长语音测试

./build/examples/k2_rnnt2_cli models/k2_rnnt2_cli/ long.wav

程序输出

Audio time is 1781.655518 s. len is 28506489
Model initialization takes 0.283899s.
Result: "听众朋友您下面将要听到的是世界文学宝库中的珍品海明威最优秀的作品老人与海
................................................................................
................................................................................
................................................................................
那么祝你晚安早上我去叫醒你你是我的闹钟男孩说呵呵年纪是我的闹钟老人说为什么老头醒
醒那么早啊难道是要让白白长一些吗我不知道我只知道少年睡得沉起得晚嗯我记在心上了到
时候会去叫醒你的我不愿让船主人来叫醒我这样似乎我比他差劲儿了自我懂安睡吧老大爷男
孩儿走出屋去"
Model inference takes 238.797095s.

k2_rnnt2模型测试

第一个参数为预训练模型存放的目录;
第二个参数为需要识别的语音文件。

./build/examples/k2_rnnt2_cli models/k2_rnnt2_cli/ zh.wav

程序输出

Audio time is 5.015000 s. len is 80240
Model initialization takes 0.211781s
result: "我认为跑步最重要的就是给我带来了身体健康"
Model inference takes 0.570641s.

长语音测试

./build/examples/k2_rnnt2_cli models/k2_rnnt2_cli/ long.wav

程序输出

Audio time is 1781.655518 s. len is 28506489
Model initialization takes 0.172187s.
Result: "听众朋友您下面将要听到的是世界文学宝库中的珍品海明威最优秀的作品老人与海
................................................................................
................................................................................
................................................................................
我也许不像我自以为那样的强壮了可是我懂得不少窍门儿而且有决心啊你该就去睡觉这样明儿
早上才精神饱满我要把这些东西送回露台饭店去啊哦好那么祝你晚安早上我去叫醒你你是我的
闹钟男孩说年纪是我的闹钟啊老人说为什么老头儿醒得那么早啊难道是要让白天长些吗我不知
道我只知道少年睡得沉起得晚啊嗯我记在心上了到时候会去叫醒你的我不愿让船主人来叫醒我
这样似乎我比他差劲儿了哼我懂安睡吧老大爷男孩儿走出屋去"
Model inference takes 186.848961s.

python wheel包测试

python examples/k2_rnnt2_cli.py models/k2_rnnt2_cli/ zh.wav

程序输出

Audio time is 4.9968125s. len is 79949.
Model initialization takes 0.8s.
Result: "我认为跑步最重要的就是给我带来了身体健康".
Model inference takes 0.57s.

conformer_wenetspeech-zh-16k模型测试

第一个参数为预训练模型存放的目录;
第二个参数为需要识别的语音文件。

./build/examples/paddlespeech_cli models/paddlespeech_cli/ zh.wav

程序输出

Audio time is 4.996812 s.
Model initialization takes 0.217759s
result: "我认为跑步最重要的就是给我带来了身体健康"
Model inference takes 1.101319s.

长语音测试

./build/examples/paddlespeech_cli models/paddlespeech_cli/ long.wav

程序输出

Audio time is 1781.655518 s. len is 28506489
Model initialization takes 0.184894s.
Result: "听众朋友您下面将要听到的是世界文学宝库中珍品海明威最优秀的作品老人于海老
................................................................................
................................................................................
................................................................................
好的渔夫是你不我知道还要比我强的哪里好渔夫很多还有些很了不起的不过点呱呱的只有你
谢谢你了你说得叫我高兴我希望不要来一条大鱼打的能证明我们都讲错了这样的鱼是没有的
只要你还是像你说的那样强壮嗯我也许不像我自以为那样的强壮可是我懂得不少窍门而且有
决心你该就去睡觉这样明儿早上才精神饱满我要把这些东西送回露台饭店去好那么祝你晚安
早上我去叫醒你你是我的闹钟男孩说年纪是我的闹钟老人说为什么老头醒得那么早啊难道是
要让白天长些吗我不知道我只知道少年睡得沉起得晚嗯我记得心上啦到时候会去叫醒你的我
不愿让船主人来叫醒我这样似乎我比他差劲儿了我懂安睡吧老大爷男孩走出屋去".
Model inference takes 351.067497s.

python wheel包测试

python examples/paddlespeech_cli.py models/paddlespeech_cli/ zh.wav

程序输出

Audio time is 4.9968125s. len is 79949.
Model initialization takes 1.1s.
Result: "我认为跑步最重要的就是给我带来身体健康".
Model inference takes 1.1s.

conformer_online_wenetspeech-zh-16k模型测试

第一个参数为预训练模型存放的目录; 第二个参数为需要识别的语音文件。

./build/examples/paddlespeech_stream models/paddlespeech_stream/ zh.wav

程序输出

Model initialization takes 0.222937s
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: ""
current result: "我认为跑"
current result: "我认为跑"
current result: "我认为跑"
current result: "我认为跑"
current result: "我认为跑"
current result: "我认为跑"
current result: "我认为跑"
current result: "我认为跑"
current result: "我认为跑步最重要的"
current result: "我认为跑步最重要的"
current result: "我认为跑步最重要的"
current result: "我认为跑步最重要的"
current result: "我认为跑步最重要的"
current result: "我认为跑步最重要的"
current result: "我认为跑步最重要的"
current result: "我认为跑步最重要的就是"
current result: "我认为跑步最重要的就是"
current result: "我认为跑步最重要的就是"
current result: "我认为跑步最重要的就是"
current result: "我认为跑步最重要的就是"
current result: "我认为跑步最重要的就是"
current result: "我认为跑步最重要的就是"
current result: "我认为跑步最重要的就是"
current result: "我认为跑步最重要的就是给我"
current result: "我认为跑步最重要的就是给我"
current result: "我认为跑步最重要的就是给我"
current result: "我认为跑步最重要的就是给我"
current result: "我认为跑步最重要的就是给我"
current result: "我认为跑步最重要的就是给我"
current result: "我认为跑步最重要的就是给我"
current result: "我认为跑步最重要的就是给我带来了"
current result: "我认为跑步最重要的就是给我带来了"
current result: "我认为跑步最重要的就是给我带来了"
current result: "我认为跑步最重要的就是给我带来了"
current result: "我认为跑步最重要的就是给我带来了"
current result: "我认为跑步最重要的就是给我带来了"
current result: "我认为跑步最重要的就是给我带来了"
current result: "我认为跑步最重要的就是给我带来了"
current result: "我认为跑步最重要的就是给我带来了身体健康"
current result: "我认为跑步最重要的就是给我带来了身体健康"
current result: "我认为跑步最重要的就是给我带来了身体健康"
current result: "我认为跑步最重要的就是给我带来了身体健康"
current result: "我认为跑步最重要的就是给我带来了身体健康"
current result: "我认为跑步最重要的就是给我带来了身体健康"
final result: "我认为跑步最重要的就是给我带来了身体健康"
Model inference takes 1.657996s.

python wheel包测试

python examples/paddlespeech_stream.py paddlespeech_stream/ zh.wav

树莓派4B上优化部署

由于深度学习推理过程,属于计算密集型算法,所以CPU的指令集对代码的执行效率会有重要影响。 从纯数值计算角度来看,64bit的指令及要比32bit的指令集执行效率要提升1倍。 经过测试同样的算法在64bit系统上,确实是要比32bit系统上,执行效率高很多。

为树莓派升级64位系统raspios

树莓派官网下载最新的raspios 64位系统, 我下载的是没有桌面的精简版raspios_lite_arm64, 当然也可以下载有桌面的版本raspios_arm64, 两者没有太大差别,全凭个人喜好。

下载完成镜像,然后烧写SD卡,保证系统新做的系统能正常启动即可。

重新编译依赖库

尽管两个依赖库fftw3和openblas都是可以通过sudo apt install直接安装的, 但是软件源上的版本是通用版本,是兼容树莓派3B等老版本的型号, 并没有针对树莓派4B的ARM CORTEX A72进行优化,所以执行效率并不高。 因此我们需要针对树莓派4B重新编译,让其发挥最大效率。

注意:以下编译安装步骤都是在树莓派上完成,不使用交叉编译!!!

安装fftw3

下载源码

wget -c http://www.fftw.org/fftw-3.3.10.tar.gz

解压

tar -xzvf fftw-3.3.10.tar.gz 
cd fftw-3.3.10/

配置工程,根据CPU选择适当的编译选项

./configure --enable-shared --enable-float --prefix=/usr

编译和安装

make -j4
sudo make install

安装OpenBLAS

下载源码

wget -c https://github.com/xianyi/OpenBLAS/releases/download/v0.3.20/OpenBLAS-0.3.20.tar.gz

解压

tar -xzvf OpenBLAS-0.3.20.tar.gz  
cd OpenBLAS-0.3.20

编译和安装

make -j4
sudo make PREFIX=/usr install

编译和测试

编译和下载预训练模型的过程,请参考上文的 源码编译安装指南章节。

运行程序

./build/examples/k2_rnnt2_cli models/k2_rnnt2_cli/ zh.wav

结果

Audio time is 4.996812 s.
Model initialization takes 10.288784s
result: "我认为跑步最重要的就是给我带来了身体健康"
Model inference takes 4.900788s.

当第一次运行时,发现模型初始化时间就用了10.2s, 显然不太合理,这是因为预训练模型是在SD卡中,一个450M大小的文件从SD卡读到内存中,主要受限于SD卡的读取速度,所以比较慢。 得利于linux的缓存机制,第二次运行时,模型已经在内存中,不用在从SD卡读取了,所以只有重启后第一次会比较慢。

第二次运行结果

Audio time is 4.996812 s.
Model initialization takes 0.797091s
result: "我认为跑步最重要的就是给我带来了身体健康"
Model inference takes 4.916471s.

从结果中可以看出,当音频文件为4.99s时,推理时间为4.91秒,推理时间小于音频时间,刚刚好能满足实时性的需求。

添加标点符号

由于ASR模型并不能处理语音中的停顿,无法直接输出标点符号,需要使用NLP方式添加标点符号,参见 : https://github.com/yeyupiaoling/PunctuationModel

相关研究方法: https://blog.csdn.net/LJJ_12/article/details/120077119

上面模型的效果比较好,缺点也明显:模型太大,速度比较慢。用于服务器端没有影响,用于客户端则影响性能。

Project details


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

fastasr-0.0.4-cp311-cp311-win_amd64.whl (12.5 MB view details)

Uploaded CPython 3.11 Windows x86-64

fastasr-0.0.4-cp311-cp311-win32.whl (7.2 MB view details)

Uploaded CPython 3.11 Windows x86

fastasr-0.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.5 MB view details)

Uploaded CPython 3.11 manylinux: glibc 2.17+ x86-64

fastasr-0.0.4-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl (2.4 MB view details)

Uploaded CPython 3.11 manylinux: glibc 2.17+ i686

fastasr-0.0.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.4 MB view details)

Uploaded CPython 3.11 manylinux: glibc 2.17+ ARM64

fastasr-0.0.4-cp311-cp311-macosx_10_9_x86_64.whl (12.1 MB view details)

Uploaded CPython 3.11 macOS 10.9+ x86-64

fastasr-0.0.4-cp310-cp310-win_amd64.whl (12.5 MB view details)

Uploaded CPython 3.10 Windows x86-64

fastasr-0.0.4-cp310-cp310-win32.whl (7.2 MB view details)

Uploaded CPython 3.10 Windows x86

fastasr-0.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.5 MB view details)

Uploaded CPython 3.10 manylinux: glibc 2.17+ x86-64

fastasr-0.0.4-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl (2.4 MB view details)

Uploaded CPython 3.10 manylinux: glibc 2.17+ i686

fastasr-0.0.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.4 MB view details)

Uploaded CPython 3.10 manylinux: glibc 2.17+ ARM64

fastasr-0.0.4-cp310-cp310-macosx_10_9_x86_64.whl (12.1 MB view details)

Uploaded CPython 3.10 macOS 10.9+ x86-64

fastasr-0.0.4-cp39-cp39-win_amd64.whl (12.5 MB view details)

Uploaded CPython 3.9 Windows x86-64

fastasr-0.0.4-cp39-cp39-win32.whl (7.2 MB view details)

Uploaded CPython 3.9 Windows x86

fastasr-0.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.5 MB view details)

Uploaded CPython 3.9 manylinux: glibc 2.17+ x86-64

fastasr-0.0.4-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl (2.4 MB view details)

Uploaded CPython 3.9 manylinux: glibc 2.17+ i686

fastasr-0.0.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.4 MB view details)

Uploaded CPython 3.9 manylinux: glibc 2.17+ ARM64

fastasr-0.0.4-cp39-cp39-macosx_10_9_x86_64.whl (12.1 MB view details)

Uploaded CPython 3.9 macOS 10.9+ x86-64

fastasr-0.0.4-cp38-cp38-win_amd64.whl (12.5 MB view details)

Uploaded CPython 3.8 Windows x86-64

fastasr-0.0.4-cp38-cp38-win32.whl (7.2 MB view details)

Uploaded CPython 3.8 Windows x86

fastasr-0.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.5 MB view details)

Uploaded CPython 3.8 manylinux: glibc 2.17+ x86-64

fastasr-0.0.4-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl (2.4 MB view details)

Uploaded CPython 3.8 manylinux: glibc 2.17+ i686

fastasr-0.0.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.4 MB view details)

Uploaded CPython 3.8 manylinux: glibc 2.17+ ARM64

fastasr-0.0.4-cp38-cp38-macosx_10_9_x86_64.whl (12.1 MB view details)

Uploaded CPython 3.8 macOS 10.9+ x86-64

fastasr-0.0.4-cp37-cp37m-win_amd64.whl (12.5 MB view details)

Uploaded CPython 3.7m Windows x86-64

fastasr-0.0.4-cp37-cp37m-win32.whl (7.2 MB view details)

Uploaded CPython 3.7m Windows x86

fastasr-0.0.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.5 MB view details)

Uploaded CPython 3.7m manylinux: glibc 2.17+ x86-64

fastasr-0.0.4-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl (2.4 MB view details)

Uploaded CPython 3.7m manylinux: glibc 2.17+ i686

fastasr-0.0.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.4 MB view details)

Uploaded CPython 3.7m manylinux: glibc 2.17+ ARM64

fastasr-0.0.4-cp37-cp37m-macosx_10_9_x86_64.whl (12.1 MB view details)

Uploaded CPython 3.7m macOS 10.9+ x86-64

fastasr-0.0.4-cp36-cp36m-win_amd64.whl (12.5 MB view details)

Uploaded CPython 3.6m Windows x86-64

fastasr-0.0.4-cp36-cp36m-win32.whl (7.2 MB view details)

Uploaded CPython 3.6m Windows x86

fastasr-0.0.4-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.5 MB view details)

Uploaded CPython 3.6m manylinux: glibc 2.17+ x86-64

fastasr-0.0.4-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl (2.4 MB view details)

Uploaded CPython 3.6m manylinux: glibc 2.17+ i686

fastasr-0.0.4-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.4 MB view details)

Uploaded CPython 3.6m manylinux: glibc 2.17+ ARM64

fastasr-0.0.4-cp36-cp36m-macosx_10_9_x86_64.whl (12.1 MB view details)

Uploaded CPython 3.6m macOS 10.9+ x86-64

File details

Details for the file fastasr-0.0.4-cp311-cp311-win_amd64.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp311-cp311-win_amd64.whl
  • Upload date:
  • Size: 12.5 MB
  • Tags: CPython 3.11, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp311-cp311-win_amd64.whl
Algorithm Hash digest
SHA256 ffd35ed7c888e0ec8370c4ba6f940885e7f1348cba0127d95a3ede481a3ce4f3
MD5 37f1ebb8692eb72ac9733275778a282b
BLAKE2b-256 e357a5c0397cdd4979d5991e1c2387bf5f3bc26b15c5b6bca439a81c6df14c1d

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp311-cp311-win32.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp311-cp311-win32.whl
  • Upload date:
  • Size: 7.2 MB
  • Tags: CPython 3.11, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp311-cp311-win32.whl
Algorithm Hash digest
SHA256 cf56eddf9d170dffa8afc816b68e1025c437e68ae8c53c63b5588a1d575b94cf
MD5 481712d66702e0f4bb03d1878ba0a6af
BLAKE2b-256 d0797296201aef002992887f69797b50dd290c080550bd058e9635e57f2897f3

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 58704e7da1bbf185c1abe9438e496be4b46fd723790ed891b9c661453b644c34
MD5 303e54955e96b572d86106a4dc526b22
BLAKE2b-256 b5c565d745dbd311f41ec058ab7a02016a864ef7a5035c9164fc7996cb3b10e0

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm Hash digest
SHA256 defa2783534394725817d68b2b57c363f8348dc0091b64eaf4cdfb92952fae38
MD5 7a7b609f63784403c8048d92ff5ec4b0
BLAKE2b-256 06fc2781ac347b0f9b955c216f45ca5385317a1a4a610c6ef9e257a697ef35f4

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 ad7eaef75027f76528c6ae800b4c8585cd8364a68c680d7e1b5410dba553310b
MD5 e2c26b6a5fa493cf6613fb532822748c
BLAKE2b-256 91eff18f860060c8480d194d2d2232748fbb758e4997915362cbd5766feef528

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp311-cp311-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp311-cp311-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 36dbcb4cf8dce3b9093253a4172b925f42af1324ef954b204687f83d05fa0b79
MD5 a6894f6e082b4046a310f9d5ae3c46df
BLAKE2b-256 d150a075d01877bc259e4b03ab2bb59f04bfdef353862547ba07c21c7f3ce6a4

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp310-cp310-win_amd64.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp310-cp310-win_amd64.whl
  • Upload date:
  • Size: 12.5 MB
  • Tags: CPython 3.10, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 5fc7d52db227da4a0b3b7912fb2f9783bf03e9bd37eaaa75314fde5f300fd5e6
MD5 58987cc5e1791b09dfb382de9e1f042e
BLAKE2b-256 20cc02c1aa6e2f59895856074d5d3ca0ab3568d34ce0043f7aec780fc113ebb6

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp310-cp310-win32.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp310-cp310-win32.whl
  • Upload date:
  • Size: 7.2 MB
  • Tags: CPython 3.10, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp310-cp310-win32.whl
Algorithm Hash digest
SHA256 449744ceb9833da2be35608dd431a96f10d119d064f70df1d6063cbb429dc0f3
MD5 83e38b2301097263c86fab78a0db8dc8
BLAKE2b-256 0be6e6cb6d6a022fed9b53e92521cbc23f950362a003403465e6e64aa1e5709f

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 27d555465bad9ad0fb44165adced755b5acc119a945710da6db55fbe4f6a4bb1
MD5 05a5a518277b3d3fc4cec149177f17f4
BLAKE2b-256 23bd171f5a2fc7a4042882c1c45d4fc4d944ee5fcd2079d1875bd9ac3a32ca90

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm Hash digest
SHA256 db2dd96bc881e9628e8bdeaecfd2f8ce3b3fa14a101675be6d8fa9c483cc4c4b
MD5 25616557c71da8672be5ac1cc1652db2
BLAKE2b-256 1eda569700ba44c60a6c1d26963f889983f62b19b97aaeeb79fa04bfbeba0584

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 4d16dbb0794091ea19ee5ceafe7e6723ebfb8e5f71fbc6acea4931821971d8e9
MD5 6ef536031a634f34a24d744f487e24ce
BLAKE2b-256 b48369dc669c730441b61d763eb572cef25c11739cb8399f9669992aaca1c0d9

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp310-cp310-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp310-cp310-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 f625cc000b5062271d0ac9231fb999ddab5315723f379c4dbebc8bafcbd94ae9
MD5 698133240fb859ecf3cafae4a9aec898
BLAKE2b-256 4e43a0b9a628e908d12f77d1239b3a11d3b31a4b3945b25ee5d74e662653323b

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp39-cp39-win_amd64.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp39-cp39-win_amd64.whl
  • Upload date:
  • Size: 12.5 MB
  • Tags: CPython 3.9, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp39-cp39-win_amd64.whl
Algorithm Hash digest
SHA256 dc748bec8fff567ab766f51dc9de5e5927b49f9438fe2da172f08e2bbe161c24
MD5 621117601b625229e7ee6e04f89ed78a
BLAKE2b-256 c9673506cc7df306f992b8727006db10f475b7b26cf0317e0b26fea3efd06fdd

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp39-cp39-win32.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp39-cp39-win32.whl
  • Upload date:
  • Size: 7.2 MB
  • Tags: CPython 3.9, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp39-cp39-win32.whl
Algorithm Hash digest
SHA256 12d913cbb8ac2110605addcc289f0b1f8705349faa4ff4ad006618eb406bf979
MD5 6453eccd903a4be4b4877adb70640860
BLAKE2b-256 c7dd3c585d28b6fefe67770d81c6bf369a3015d903f5f6975a6566b73c484ae5

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 c6a1073cb097effe0b30d1360ab684ed9253e8c6065c0085f11a36e69b7a66bc
MD5 4547a6562900da225d32031139d4f23a
BLAKE2b-256 8bf70765d7ffa23f5a260328afd0401b52bf3b9a9eec3c22c469ea203f1710fa

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm Hash digest
SHA256 0178e8387210eacc2023a551620b821f40e9a0f59979d663b4fcc969cb7b63ae
MD5 bdaea9dd58fb22d2d05fc5cb8159436d
BLAKE2b-256 63983995f9bd1487ce0115dabc78cad957ec0eacbb69bbe91451a5779c50354f

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 c733ceb1eb66562bda894f47494b81df441797d1dcd5142dde4a3a3e79f30ad5
MD5 629ee71803b92baf84572175e2830422
BLAKE2b-256 5167ce48b5d3c0b72dbf313a412e30013ff3332b7190b407c7ad510e2ec276c2

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp39-cp39-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp39-cp39-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 82ec775f4cfc3ff61742c0357981728158241e94973c05bebcfa34a9a5cfce6b
MD5 71eac2fbeca17121399ac7aea2429d94
BLAKE2b-256 78b52f2921c0c989459cca444f9f61dc82a35bb8098c72604abf9c6394bb0d0a

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp38-cp38-win_amd64.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp38-cp38-win_amd64.whl
  • Upload date:
  • Size: 12.5 MB
  • Tags: CPython 3.8, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp38-cp38-win_amd64.whl
Algorithm Hash digest
SHA256 3b2806845ac58393624dd7226abd0ad8d6c027036dca1511109c77a096b0f781
MD5 9b027fd212b6c46498ed8f510c0975c3
BLAKE2b-256 49bab88dd28a71fe51490a7b065a2978406b5295ed0bd1aeb5d8597fc39a3add

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp38-cp38-win32.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp38-cp38-win32.whl
  • Upload date:
  • Size: 7.2 MB
  • Tags: CPython 3.8, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp38-cp38-win32.whl
Algorithm Hash digest
SHA256 94374b15ae82a7d6bdf9643ce7dbcf1ad97d22e031c1b2b18a636b429a0bc2f9
MD5 d82e94cc76dcb8682c3e8729c0f356fe
BLAKE2b-256 2cef02ceb9148d609112c341587561e62504061580c6f589dc54bb4ed730df6d

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 8f0c4af6ce82ef75e54165fdd2acee241ee68eec5b9bb6b281c6b17a0bab1dd4
MD5 7454c71fff9982569937ceece91a03ff
BLAKE2b-256 789c3ab7e30494084d8439275c477142f4a47f667c56470b43eb1436a0060662

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm Hash digest
SHA256 1ff8cdc78ce48cda050e9d052a42e36c2edb1fdbc48256627230b2cfc415d6d6
MD5 f1a92ea3648c92dece807b94c86fb52d
BLAKE2b-256 7abf9a69f85ca0e53fad37511bd7c9c3bfb62df7d2832692cd7708615d97750d

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 211c442452bb61ae0801a87442ee5483fb7f573b4eed3d78080483dd3bf8999d
MD5 3581c8c82246b39f137f3444bc60fab0
BLAKE2b-256 db71d7c1d5751ae74542baa7624b5044587d558f54cd3d14c599b812ece8527c

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp38-cp38-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp38-cp38-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 f39a71798cd530eee9419cd97c65ad6890afb88e69e726073559bde93c55e737
MD5 3696509e2a0d473a6b224d71bd49c8d9
BLAKE2b-256 25306d2a5c056ec11cf3d11ecb4ee9ddf856b76c309eb5ecc8e53a259cc32b25

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 12.5 MB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 492d361d2e8573d897906476ccbbc315059da6420d2c1c84dc3e9b01c2e46770
MD5 4f144b2d4cad3d36bc0fd2831694ce15
BLAKE2b-256 74b73e747b4919f974628fafdaeb5a1ac55c3ce92a3857b23a9b71c3b76e5d98

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp37-cp37m-win32.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp37-cp37m-win32.whl
  • Upload date:
  • Size: 7.2 MB
  • Tags: CPython 3.7m, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp37-cp37m-win32.whl
Algorithm Hash digest
SHA256 9f15a57bf1329a506b58da24abab4973b1423c2cd0d9627f1f9dd546fcd5dfbf
MD5 505a6f15f4e6ecdfa8712d618a9fd23f
BLAKE2b-256 8596b66635e979d06e2f54ec10b62b0040d60852672f4df0a9cb5182f5d75050

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 2818fe51c7c751b1248f880e392b53bf034a521e125185461c01228984cb0471
MD5 f7f0bacb461ffe17f65257b33bede528
BLAKE2b-256 3e6abcb693f570587e6536dd9c0b7929d74a9eeb929d924be8761c1a887cf296

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm Hash digest
SHA256 6e540d37238065bd14a605b1e38d8f186e792b8524166c24e15574e0132e062a
MD5 48594b1afe47f809f7659e913e949fbc
BLAKE2b-256 96cc97571af8c7fd32e72929ae498dd616d8d36aa151744c08ac8c1a67ce30f7

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 4aa9b3eb572b1f1c81fbfc949547767aac6ba0d0f1d2cdc7ab07b3b10de73ff0
MD5 97176d893e875e15df62ed1b7cc900cd
BLAKE2b-256 8d7354e2b5700c3f6dddba3b04b56218214f885a50c67811490c191b21781267

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp37-cp37m-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp37-cp37m-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 7375978581fd0948b92b05976e70c978a610c79230d7cd42b295cdad4620542d
MD5 6424a91bc05bc6515bee84bfc2de4bcc
BLAKE2b-256 560c5871b8fd5c0d64def3df86b3e5263c9e33604d25ac39b26b08165d61f02e

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 12.5 MB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 b175235b1c9682f8e665f4850299394370fd0fd31dcd51d0202f9696e16545ac
MD5 506302b2cbe59f88e6846ee4b913d07a
BLAKE2b-256 52ff0c691102ef848376a2e876f63f43d5d2d38dd73748daaa4f20f8e74341a2

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp36-cp36m-win32.whl.

File metadata

  • Download URL: fastasr-0.0.4-cp36-cp36m-win32.whl
  • Upload date:
  • Size: 7.2 MB
  • Tags: CPython 3.6m, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for fastasr-0.0.4-cp36-cp36m-win32.whl
Algorithm Hash digest
SHA256 533268735afeb1609cfbc8b6d0f2a5fe9b0efc45d807ecfdc01987c3886b6b8c
MD5 4970b713262eebdd154548560b279cc9
BLAKE2b-256 2c2f6a6f5218c9e1af9925786f8c8bb87b5387aeccbddb827cc1f84dd74a8b30

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 215e5e776e9e734494ffbc120172c40e86e5106362c0a2058eaeabac64ea5787
MD5 9901b70912f38448532214e1f21d9aa3
BLAKE2b-256 92eac94f38810e864ae12aa9af6ecf567676f3037cbb8282deedc0c46d04870d

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm Hash digest
SHA256 6845931c2b6dfbb31f643610409ae0c83e7c7e945d75f68ede0e4a42a037ca7a
MD5 3d7c04cd3347376849ea59b96f549800
BLAKE2b-256 db612a1d8dc74a0554c1df328c6d3bf799a5354a03ad4ea37b1ef820e427eccc

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 960fc6db39d3f234859826504724c7a9741f7bf86d6659da15015618c79a826b
MD5 43fa83626b1d1a94f0e11cb6c95c74c9
BLAKE2b-256 f94ec6931966198e6c6866bdd0549b6608f6b8b130b24d6fb875bf48c4f55128

See more details on using hashes here.

File details

Details for the file fastasr-0.0.4-cp36-cp36m-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for fastasr-0.0.4-cp36-cp36m-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 60f4a33874009a202d1d2ea72d4e4fe705128b31e1d948f77fa10fa75a92bcd1
MD5 f3a3be566089241f5bd4a007759ac2ce
BLAKE2b-256 9f9872e1ed38acef31f9b49715b1b0e65d9c7757ea58fd9232256294e5c0e278

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page