You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
我在主板的官网找到声卡驱动realtek audio，安装之后已经成功的在win11的声音输入设置：立体声混音，但是字幕还是没有成功显示，不知道为什么？以下和附件我附上使用echo-v1.1.0-debug.exe得到的报错信息，请帮我看一下问题出在哪里？谢谢。
###
parse config succeed, use it
parse config succeed, use it
try to init vosk asr engine
use asr-server-v1.1.0
asrDir exists, start asr server C:\Users\BenSa\Downloads\echo-v1.1.0.exe\echo\asr-server-v1.1.0
try to init nlp engine
use nlp-server
nlpDir exists, start nlp server C:\Users\BenSa\Downloads\echo-v1.1.0.exe\echo\nlp-server
stdout: 2023-05-10 21:28:25.974 INFO : NLP API is starting, please wait...
stdout: 2023-05-10 21:28:25.974 INFO : NLP-API model dir: C:\Users\BenSa\Downloads\echo-v1.1.0.exe\echo\nlp-server\model
stdout: 2023-05-10 21:28:27.055 INFO : ASR API is starting, please wait...
stdout: torch info:
2.0.0+cpu
None
False
stdout: 2023-05-10 21:28:30.086 INFO : NLP API has been started
Endpoint: POST http://127.0.0.1:8100/translate
Language: en to zh
nlp server started
(node:6776) UnhandledPromiseRejectionWarning: AxiosError: Request failed with status code 404
at settle (C:\snapshot\dist\_\_\app.js)
at IncomingMessage.handleStreamEnd (C:\snapshot\dist\_\_\app.js)
at IncomingMessage.emit (events.js:412:35)
at endReadableNT (internal/streams/readable.js:1333:12)
at processTicksAndRejections (internal/process/task_queues.js:82:21)
(Use `echo-v1.1.0-debug --trace-warnings ...` to show where the warning was created)
(node:6776) UnhandledPromiseRejectionWarning: Unhandled promise rejection. This error originated either by throwing inside of an async function without a catch block, or by rejecting a promise which was not handled with .catch(). To terminate the node process on unhandled promise rejection, use the CLI flag `--unhandled-rejections=strict` (see https://nodejs.org/api/cli.html#cli_unhandled_rejections_mode). (rejection id: 2)
(node:6776) [DEP0018] DeprecationWarning: Unhandled promise rejections are deprecated. In the future, promise rejections that are not handled will terminate the Node.js process with a non-zero exit code.
stderr: transformers\pipelines\token_classification.py:157: UserWarning: `grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="none"` instead.
warnings.warn(
stdout: 2023-05-10 21:28:32.484
stdout: advance model exists: False
INFO : init end
model path: C:\Users\BenSa\Downloads\echo-v1.1.0.exe\echo\asr-server-v1.1.0\./model/vosk-model-en-us-0.22-lgraph
stderr: INFO:ASR-API:init end
stdout: 2023-05-10 21:28:32.529 INFO : ASR API has been started
Endpoint: POST http://127.0.0.1:8200/asr
asr server started
stderr: INFO:ASR-API:ASR API has been started
Endpoint: POST http://127.0.0.1:8200/asr
stderr: INFO:root:will run asr client
stderr: INFO:websockets.server:server listening on 0.0.0.0:8210
stderr: INFO:websockets.server:connection open
stderr: INFO:root:Connection from ('127.0.0.1', 60621)
stderr: INFO:root:Config {'sample_rate': 16000}
###
在 2023-05-11 08:53:32，"rerender2021" ***@***.***> 写道：
win11：可以试试搜搜解答：
https://answers.microsoft.com/zh-hans/windows/forum/all/win11%E6%B2%A1%E6%9C%89%E7%AB%8B%E4%BD%93%E5%A3%B0/255778cb-dde4-43d8-97dc-98891545bb24https://www.ylmfwin100.net/ylmf/8942.html
Voicemeeter：我没有使用过这个进行测试
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
parse config succeed, use it
parse config succeed, use it
try to init vosk asr engine
use asr-server-v1.1.0
asrDir exists, start asr server C:\Users\BenSa\Downloads\echo-v1.1.0.exe\echo\asr-server-v1.1.0
try to init nlp engine
use nlp-server
nlpDir exists, start nlp server C:\Users\BenSa\Downloads\echo-v1.1.0.exe\echo\nlp-server
stdout: 2023-05-10 21:28:25.974 INFO : NLP API is starting, please wait...
stdout: 2023-05-10 21:28:25.974 INFO : NLP-API model dir: C:\Users\BenSa\Downloads\echo-v1.1.0.exe\echo\nlp-server\model
stdout: 2023-05-10 21:28:27.055 INFO : ASR API is starting, please wait...
stdout: torch info:
2.0.0+cpu
None
False
stdout: 2023-05-10 21:28:30.086 INFO : NLP API has been started
Endpoint: POST http://127.0.0.1:8100/translate
Language: en to zh
nlp server started
(node:6776) UnhandledPromiseRejectionWarning: AxiosError: Request failed with status code 404
at settle (C:\snapshot\dist\_\_\app.js)
at IncomingMessage.handleStreamEnd (C:\snapshot\dist\_\_\app.js)
at IncomingMessage.emit (events.js:412:35)
at endReadableNT (internal/streams/readable.js:1333:12)
at processTicksAndRejections (internal/process/task_queues.js:82:21)
(Use `echo-v1.1.0-debug --trace-warnings ...` to show where the warning was created)
(node:6776) UnhandledPromiseRejectionWarning: Unhandled promise rejection. This error originated either by throwing inside of an async function without a catch block, or by rejecting a promise which was not handled with .catch(). To terminate the node process on unhandled promise rejection, use the CLI flag `--unhandled-rejections=strict` (see https://nodejs.org/api/cli.html#cli_unhandled_rejections_mode). (rejection id: 2)
(node:6776) [DEP0018] DeprecationWarning: Unhandled promise rejections are deprecated. In the future, promise rejections that are not handled will terminate the Node.js process with a non-zero exit code.
stderr: transformers\pipelines\token_classification.py:157: UserWarning: `grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="none"` instead.
warnings.warn(
stdout: 2023-05-10 21:28:32.484
stdout: advance model exists: False
INFO : init end
model path: C:\Users\BenSa\Downloads\echo-v1.1.0.exe\echo\asr-server-v1.1.0\./model/vosk-model-en-us-0.22-lgraph
stderr: INFO:ASR-API:init end
stdout: 2023-05-10 21:28:32.529 INFO : ASR API has been started
Endpoint: POST http://127.0.0.1:8200/asr
asr server started
stderr: INFO:ASR-API:ASR API has been started
Endpoint: POST http://127.0.0.1:8200/asr
stderr: INFO:root:will run asr client
stderr: INFO:websockets.server:server listening on 0.0.0.0:8210
stderr: INFO:websockets.server:connection open
stderr: INFO:root:Connection from ('127.0.0.1', 60621)
stderr: INFO:root:Config {'sample_rate': 16000}
1. 输入立体声下面的麦克风条没有跳动（如附件的图）
2. 复制的文本已经是全部的文本了
3. 软件的目录地址是下载echo只有解压的路劲，只是测试好这个软件之后就会放到D盘的program文件夹去的，这个路径只是方面临时测试而已
如果视频的音频没有到输入立体声去的，那该怎么办呢？非常感谢
在 2023-05-12 09:11:01，"rerender2021" ***@***.***> 写道：
在播放视频的时候，立体声混音下面的麦克风条有跳动吗，需要确认设置是否有效
复制的文本是所有内容吗，通常在播放视频的时候，还会有识别到的语音文本输出，这里没有，说明没有语音识别成功
“ C:\Users\BenSa\Downloads*echo-v1.1.0.exe*\echo” 这个目录看起来有点奇怪，文件夹有.exe结尾的
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
1. 哦，可能你在注册github的邮箱上看的话会看到附件的图片
2. 我的是外置声卡，能输入midi乐器，但没有话筒的输入。所以在win11的设置中，在输入哪里没法算立体声混音，但是我在youtube找能使得板载的声卡有立体声混音了方法，1. CMD->gpupdate，2.官网下载Realtek进行安装。这样的确在设置的声音输入里有了立体声混音。但是如你所见，电脑的声音就是没有到输入的地方去
3. voicemeeter我用过，win11设置-声音-输入里已经成功显示了voicemeeter，但是结果echo还是没有成功显示字幕。
我看你网站的说明win10设置立体声输入，使用的就是Realtek啊？我安装的也是这个板载声卡驱动，但为什么就是不行？
还有voicemeeter安装之后，虽然win11设置-声音-输入里已经成功显示了voicemeeter，是不是还要设置些什么啊？
在 2023-05-13 07:12:53，"rerender2021" ***@***.***> 写道：
“如附件的图”：我这边看不到附件的图
"视频的音频没有到输入立体声"
你的声卡有什么特殊之处吗？只是普通电脑，还是说有专门配备过声卡相关设备。这里有一例独立声卡立体声混音可选择但无效对的：rerender2021/language-shadow#4 (comment)
是否使用的是耳机，这里有一例使用耳机立体声混音无效的：#4 (comment)
另外这有一例立体声混音也无效的：#4 (comment)
解决方式：由于我没有遇到过，所以也只能通过搜索来看：
直接解决：比如知乎/搜索引擎上搜：https://www.zhihu.com/question/369514312 这里提到驱动版本可能有关
绕过这个问题：安装虚拟声卡，比如这里的用户后来改用
成功的，如果你无法成功，另外也可搜教程换其它虚拟声卡 https://www.443w.com/tts/?post=59
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
Activity
rerender2021 commentedon May 11, 2023
win11：可以试试搜搜解答：
Voicemeeter：我没有使用过这个进行测试
BenPong commentedon May 11, 2023
rerender2021 commentedon May 12, 2023
BenPong commentedon May 12, 2023
rerender2021 commentedon May 12, 2023
“如附件的图”：我这边看不到附件的图
"视频的音频没有到输入立体声"
你的声卡有什么特殊之处吗？只是普通电脑，还是说有专门配备过声卡相关设备。这里有一例独立声卡立体声混音可选择但无效对的：rerender2021/language-shadow#4 (comment)
是否使用的是耳机，这里有一例使用耳机立体声混音无效的：#4 (comment)
另外这有一例立体声混音也无效的：#4 (comment)
解决方式：由于我没有遇到过，所以也只能通过搜索来看：
BenPong commentedon May 14, 2023
rerender2021 commentedon May 15, 2023
这种设备问题比较复杂了，我没有这方面的经验，比如我没有外置声卡，不知道是不是用自带的声卡的时候需要先怎么关掉它? 会不会有影响。这种只能根据自己的情况搜索解决了：比如这里似乎和使用耳机/接口也有关系：https://answers.microsoft.com/zh-hans/windows/forum/all/win11%E6%97%A0%E6%B3%95%E5%9C%A8%E4%BD%BF%E7%94%A8/9c48a68b-cb25-4711-b6bb-7ee617e59c70
voicemeeter可以问问链接里那位成功使用的交流一下：能不能让它通过语音识别 language-shadow#4 (comment) 或者试试其它虚拟声卡