OpenAI Whisper探索(一)
1.根据提示安装依赖 ：
安装Whisper前先安装依赖
1.1安装torch：
ERROR: Could not find a version that satisfies the requirement torch (from versions: none)
经过了解torch是
pip install torch
Looking in indexes: https://mirrors.aliyun.com/pypi/simple/
Collecting torchDownloading https://mirrors.aliyun.com/pypi/packages/a6/41/122f37c99422566ea74b9cce90eb9218f5e8fb2582466da220f95842a0a0/torch-1.13.1-cp38-cp38-win_amd64.whl (162.6 MB)---------------------------------------- 162.6/162.6 MB 502.9 kB/s eta 0:00:00
Requirement already satisfied: typing-extensions in 。。。 (from torch) (3.10.0.2)
Installing collected packages: torch
Successfully installed torch-1.13.1
- PS： 运行的时候还会遇到提示缺少VC环境，按照提示地址下载安装就可以了
Microsoft Visual C++ Redistributable is not installed, this may lead to the DLL
load failure.
It can be downloaded at https://aka.ms/vs/16/release/vc_redist.x64.exe
OSError: [WinError 126] 找不到指定的模块。 Error loading “c:\python\python38\lib
\site-packages\torch\lib\c10.dll” or one of its dependencies.
1.2安装transformers
ERROR: Could not find a version that satisfies the requirement transformers>=4.19.0 (from whisper) (from versions: none)
pip install transformers
Looking in indexes: https://mirrors.aliyun.com/pypi/simple/
Collecting transformersDownloading https://mirrors.aliyun.com/pypi/packages/90/5b/02becd3e137fdacdc30c6442d04094d0b92e500f978df00b1a197b68fd2b/transformers-4.25.1-py3-none-any.whl (5.8 MB)---------------------------------------- 5.8/5.8 MB 670.1 kB/s eta 0:00:00
Installing collected packages: tokenizers, regex, packaging, filelock, huggingface-hub, transformers
Successfully installed filelock-3.8.2 huggingface-hub-0.11.1 packaging-22.0 regex-2022.10.31 tokenizers-0.13.2 transformers-4.25.1
1.3安装ffmpeg-python
ERROR: Could not find a version that satisfies the requirement ffmpeg-python==0.2.0 (from whisper) (from versions: none)
pip install ffmpeg-python
Looking in indexes: https://mirrors.aliyun.com/pypi/simple/
Collecting ffmpeg-pythonDownloading https://mirrors.aliyun.com/pypi/packages/d7/0c/56be52741f75bad4dc6555991fabd2e07b432d333da82c11ad701123888a/ffmpeg_python-0.2.0-py3-none-any.whl (25 kB)
Requirement already satisfied: future in h:\program files\python\python38\lib\site-packages (from ffmpeg-python) (0.18.2)
Installing collected packages: ffmpeg-python
Successfully installed ffmpeg-python-0.2.0
。。。根据提示安装其他依赖
2.安装完所有依赖后安装whisper
pip install git+https://github.com/openai/whisper.git
Looking in indexes: https://mirrors.aliyun.com/pypi/simple/
Collecting git+https://github.com/openai/whisper.gitCloning https://github.com/openai/whisper.git to 。。。。\local\temp\pip-req-build-wj07mmuzRunning command git clone --quiet https://github.com/openai/whisper.git '。。。。\Local\Temp\pip-req-build-wj07mmuz'Resolved https://github.com/openai/whisper.git to commit 0b5dcfdef7ec04250b76e13f1630e32b0935ce76Preparing metadata (setup.py) ... done
Requirement already satisfied: numpy in 。。。 (from whisper==1.0) (1.18.4)
Requirement already satisfied: torch in 。。。 (from whisper==1.0) (1.13.1)
Requirement already satisfied: tqdm in 。。。 (from whisper==1.0) (4.48.0)
Requirement already satisfied: more-itertools in 。。。 (from whisper==1.0) (8.5.0)
Requirement already satisfied: transformers>=4.19.0 in 。。。 (from whisper==1.0) (4.25.1)
Requirement already satisfied: ffmpeg-python==0.2.0 in 。。。 (from whisper==1.0) (0.2.0)
Requirement already satisfied: future in 。。。 (from ffmpeg-python==0.2.0->whisper==1.0) (0.18.2)
Requirement already satisfied: regex!=2019.12.17 in 。。。 (from transformers>=4.19.0->whisper==1.0) (2022.10.31)
Requirement already satisfied: huggingface-hub<1.0,>=0.10.0 in 。。。 (from transformers>=4.19.0->whisper==1.0) (0.11.1)
Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in 。。。 (from transformers>=4.19.0->whisper==1.0) (0.13.2)
Requirement already satisfied: pyyaml>=5.1 in 。。。 (from transformers>=4.19.0->whisper==1.0) (5.4.1)
Requirement already satisfied: requests in 。。。 (from transformers>=4.19.0->whisper==1.0) (2.23.0)
Requirement already satisfied: packaging>=20.0 in 。。。 (from transformers>=4.19.0->whisper==1.0) (22.0)
Requirement already satisfied: filelock in 。。。 (from transformers>=4.19.0->whisper==1.0) (3.8.2)
Requirement already satisfied: typing-extensions in 。。。 (from torch->whisper==1.0) (3.10.0.2)
Requirement already satisfied: idna<3,>=2.5 in 。。。 (from requests->transformers>=4.19.0->whisper==1.0) (2.9)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in 。。。 (from requests->transformers>=4.19.0->whisper==1.0) (1.25.9)
Requirement already satisfied: certifi>=2017.4.17 in 。。。 (from requests->transformers>=4.19.0->whisper==1.0) (2020.4.5.1)
Requirement already satisfied: chardet<4,>=3.0.2 in 。。。 (from requests->transformers>=4.19.0->whisper==1.0) (3.0.4)
Installing collected packages: whisperDEPRECATION: whisper is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at https://github.com/pypa/pip/issues/8559Running setup.py install for whisper ... done
Successfully installed whisper-1.0
下载引用models文件所在默认路径
%UserProfile%\.cache\whisper
OpenAI Whisper探索(一)相关推荐
- OpenAI Whisper and ChatGPT 语音助手
OpenAI Whisper and ChatGPT ASR Gradio Web UI 一 环境准备 1.1 python 1.2 windows 二 导入所需要的包 三 加载模型 四 定义open ...
- OpenAI Whisper + FFmpeg + TTS：动态实现跨语言视频音频翻译
本文作者系360奇舞团前端开发工程师 摘要: 本文介绍了如何结合 OpenAI Whisper.FFmpeg 和 TTS(Text-to-Speech)技术,以实现将视频翻译为其他语言并更换声音的过程 ...
- AI创作教程之从 Youtube平台视频剪辑生成新闻文章 基于OpenAI Whisper、OpenAI GPT3 和 Stable Diffusion
在这篇文章中,我想展示如何借助不同的软件工具从 Youtube 上发布的新闻剪辑中全自动生成包含文本和图像的新闻文章.使用当前用于处理媒体数据的 AI 模型,例如 OpenAI Whisper.Ope ...
- 使用OpenAI的Whisper 模型进行语音识别
语音识别是人工智能中的一个领域,它允许计算机理解人类语音并将其转换为文本.该技术用于 Alexa 和各种聊天机器人应用程序等设备.而我们最常见的就是语音转录,语音转录可以语音转换为文字记录或字幕. w ...
- 如何一键生成字幕，如何快速处理生肉资源？借助whisper语音识别系统生成.srt字幕文件 手把手教学在Windows、CPU版本下whisper的安装与使用，快速上手！
目录 一.前言 二.本机环境 三.安装步骤: 步骤1:下载Git并添加环境变量 步骤2:下载ffmpeg并添加环境变量 步骤3:安装pytorch 步骤4:安装whisper 四.whisper的应用 ...
- 如何在矩池云上安装语音识别模型 Whisper
如何在矩池云上安装语音识别模型 Whisper Whisper 是 OpenAI 近期开源的一个语音识别的模型,研究人员基于 680,000 小时的标记音频数据进行训练,它同时也是一个多任务模型,可以 ...
- 已达到人类水准语音识别模型的whisper，真的有这么厉害吗？
嗨,好久不见,很长时间没有写东西了,所以今天来简单的带大家了解一下语音识别模型Whisper. Whisper是openai在9月发布的一个开源语音识别翻译模型,它的英语翻译的鲁棒性和准确性已经达到了 ...
- 语音识别 - ASR whisper
目录 1. 简单介绍 2. 代码调用 1. 简单介绍 Introducing Whisperhttps://openai.com/blog/whisper/ OpenAI 的开源自动语音识别神经网络 ...
- 输入文本就可建模渲染了？！OpenAI祭出120亿参数魔法模型！
转自:https://new.qq.com/omn/20210111/20210111A0CBRD00.html 2021刚刚开启,OpenAI又来放大招了! 能写小说.哲学语录的GPT-3已经不足为 ...
最新文章
- opencv 凹凸性检测 和 缺陷分析
- getBoundingClientRect()方法
- [机器学习]AutoML --- AutoKeras
- 面试时Android屏幕适配,Android—屏幕适配(面试技巧)
- jsp mysql登录 demo_java jsp+servlet+mysql实现登录网页设计
- 关于获取多个屏幕分辨率以及进行一些设置
- SpringSecurity使用SpringBoot简单使用
- Yii2框架之旅（六）
- python列表的嵌套_Python 展开多层嵌套的列表
- ubuntu 16.04/14.04 ORK 在 Kinect v2和 Kinect v1的安装（物体位姿估计）
- wordpress字体_如何在WordPress中使用网络字体
- 基于微信小程序的校园论坛系统开发过程
- 【ADRC】自抗扰控制
- 基于51单片机机械臂控制系统
- JS监听页面刷新及阻止页面刷新
- 开学季好物怎么选，学生党必备的几款好物分享
- 【ZF】论文相似度检测 免费论文检测
- 可见光通信技术的原理、结构及应用研究
- 电子计算机工作最主要特征,电子计算机最重要的工作特征是（ ）
- Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection