{"id":25232924,"url":"https://github.com/aidayang/funasr-oneclick","last_synced_at":"2025-10-24T05:12:04.628Z","repository":{"id":276724903,"uuid":"930086893","full_name":"aidayang/FunASR-OneClick","owner":"aidayang","description":"FunASR实时语音识别版，识别麦克风和电脑内播放的声音，电脑语音打字软件","archived":false,"fork":false,"pushed_at":"2025-02-17T11:37:58.000Z","size":3,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-17T12:32:15.508Z","etag":null,"topics":["audio-visual-speech-recognition","conformer","dfsmn","funasr","paraformer","pretrained-models","punctuation","pytorch","rnnt","speaker-diarization","speech-recognition","speechgpt","speechllm","vad","voice-activity-detection","whisper"],"latest_commit_sha":null,"homepage":"https://nuowa.net/1675","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aidayang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-10T03:32:49.000Z","updated_at":"2025-02-17T11:38:02.000Z","dependencies_parsed_at":"2025-02-10T04:37:45.289Z","dependency_job_id":null,"html_url":"https://github.com/aidayang/FunASR-OneClick","commit_stats":null,"previous_names":["aidayang/funasr-oneclick"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidayang%2FFunASR-OneClick","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidayang%2FFunASR-OneClick/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidayang%2FFunASR-OneClick/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidayang%2FFunASR-OneClick/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aidayang","download_url":"https://codeload.github.com/aidayang/FunASR-OneClick/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247362934,"owners_count":20926857,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["audio-visual-speech-recognition","conformer","dfsmn","funasr","paraformer","pretrained-models","punctuation","pytorch","rnnt","speaker-diarization","speech-recognition","speechgpt","speechllm","vad","voice-activity-detection","whisper"],"created_at":"2025-02-11T13:37:05.226Z","updated_at":"2025-10-24T05:12:04.623Z","avatar_url":"https://github.com/aidayang.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# FunASR-OneClick\nFunASR实时语音识别版免安装一键启动整合包，识别麦克风和电脑内播放的声音转为文字\n\n### 2025-09-12 更新批量音视频文件识别转文字版本\n\n![](https://raw.githubusercontent.com/aidayang/FunASR-OneClick/refs/heads/main/asrv5.webp)\n\n## FunASR整合包说明\nFunASR是阿里推出的一款语音识别转文字应用，我基于这个应用做了一个实时版的语音识别转文字软件，可以实时识别麦克风输入的声音或是电脑内播放的声音，支持实时翻译\n为了方便大家快速上手体验，省去安装部署耗时，我制作了最新版免安装一键启动整合包\n\n2025-06-01\n\n更新V5版本，更新主程序，更新UI\n\n## FunASR整合包使用教程\n软件下载解压后直接双击【启动软件.exe】即可启动。软件操作界面比较简单\n\n首先选择识别内容保存位置，识别结果输出文件格式为txt\n\n块长度和上下文长度决定了最终的识别效果，块长度值越大，相同语速下每段识别出的内容的字数越多，上下文长度值建议是块长度值的1/2，这两个值越大，识别出的文字内容越准确，但是延迟也越高，这个可以自行测试效果，选择合适的值\n\n音量阈值就是用于屏蔽低音噪音的，如果说话人环境比较嘈杂，可以设置该值，屏蔽掉低音噪音部分，值越大，屏蔽的声音分贝越高，也就是屏蔽的声音越多\n\n翻译工具国内用户用百度，国外用户用谷歌，免费申请百度翻译API可以查看下面教程《最新百度翻译api免费申请AppId和AppSecret流程，每月免费100万字符》\n\n如果你想翻译成的目标语言在列表里没有，可自行设置语言代码，百度翻译和Google翻译语言代码参考下面文章《百度翻译谷歌翻译API语言代码名称对照表》，将所需要的语言代码填入目标语言输入框里即可\n\n由于软件是收集一定长度的识别文本之后再将文本提交到翻译工具进行翻译，然后收到返回翻译结果再进行显示，所以翻译文本和识别的文本有时间差，不会同步显示\n\n待翻译文本长度的意思就是一次性提交给翻译工具的文本长度，软件并不是每次识别出内容之后都提交给翻译工具的，而是收集到一定长度的文本内容之后再发送给翻译工具进行翻译。发送给翻译工具的文本越短，翻译结果越不准确，发送的文本越长，翻译工具越能综合上下文意思翻译的更准确，但是收集的文本越长等待时间也就越长，可自行取舍。一个英文字母算一个字符，一个汉字也算一个字符，如果是类似英语语言这个值建议大一点\n\n软件支持识别电脑内播放的声音或是麦克风等外部输入的声音。如果需要识别电脑内播放的声音，需要先进行电脑设置，鼠标右键点击电脑屏幕右下角音量喇叭图标，选择 【声音】，点击录制选项卡，鼠标右键点击【立体声混音】，选择【设置为默认设备】，如果立体声混音没启动的话，需要先启用，然后运行软件开始处理，就可以实时识别电脑播放声音了。\n\n如果想同时接收麦克风声音和电脑内播放声音，可在软件音频源中选择电脑播放声音，电脑声音设置里-录制-麦克风，点击鼠标右键，选择麦克风属性，勾选【侦听此设备】\n\n字幕文本显示长度就是前端实时显示语音识别出的文本的字幕字符长度\n\n如果无法使用的话，可以勾选显示调试窗口查看报错信息\n\n软件使用视频教程：https://www.youtube.com/watch?v=_Kj05EsS3_8\n\n## 注意事项\n本软件只支持识别中英文，不支持识别其它语言\n\n软件运行路径中不要出现中文及空格，否则会报错\n\n软件只支持win10或win11，不支持其他版本Windows系统，也不支持手机和MAC\n\n有部分Win11用户发现软件无法检测到音频，也就是电脑立体声混音没有音频输入，可以安装voicemeeter虚拟声卡解决。在【1 HARDWARE INPUT】设置硬件声音输入设备，在【VIRTUAL INPUT】选中【B】，在【HARDWARE OUT】选择声音输出设备，然后打开电脑系统-声音-录制，将默认设备选择为VoiceMeeter VAIO3 Output\n\n## FunASR电脑实时语音识别转文字整合包下载链接\n\nhttps://pan.quark.cn/s/4ae36edd5858\n\n## 音视频文件识别版本下载链接\nhttps://pan.quark.cn/s/8327dfd8a5b1\n\n## FunASR项目地址\n\nhttps://github.com/modelscope/FunASR\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faidayang%2Ffunasr-oneclick","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faidayang%2Ffunasr-oneclick","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faidayang%2Ffunasr-oneclick/lists"}