Show HN: Ermine.ai – Record and transcribe speech, 100% client-side (WASM)

I&#x27;m after something that can transcribe medical notes and unfortunately it does not work well for that case. (almost nothing does though) There&#x27;s quite a few people interested in something that doesn&#x27;t turn &quot;laparoscopic&quot; into &quot;leper as cop it&quot;.<p>Maybe the current progress will help though. Models adjusted by your own dictionary or from postprocessing fixes would be amazing.

Nice!<p>Are you aware that whisper.cpp has a WASM-version as well? See <a href="https:&#x2F;&#x2F;github.com&#x2F;ggerganov&#x2F;whisper.cpp&#x2F;tree&#x2F;master&#x2F;examples&#x2F;whisper.wasm">https:&#x2F;&#x2F;github.com&#x2F;ggerganov&#x2F;whisper.cpp&#x2F;tree&#x2F;master&#x2F;example...</a> - demo at <a href="https:&#x2F;&#x2F;whisper.ggerganov.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;whisper.ggerganov.com&#x2F;</a>

When I try this on Firefox on Linux (not incognito) I get the following error:<p><pre><code> Connecting AudioNodes from AudioContexts with different sample-rate is currently not supported. index-0dae94e71b526640.js:1:2992 Uncaught (in promise) DOMException: AudioContext.createMediaStreamSource: Connecting AudioNodes from AudioContexts with different sample-rate is currently not supported. index-0dae94e71b526640.js:1 Media resource blob:https:&#x2F;&#x2F;www.ermine.ai&#x2F;e762a6f1-f292-4b23-96e0-8059a7f9d635 could not be decoded. www.ermine.ai Media resource blob:https:&#x2F;&#x2F;www.ermine.ai&#x2F;e762a6f1-f292-4b23-96e0-8059a7f9d635 could not be decoded, error: Error Code: NS_ERROR_DOM_MEDIA_METADATA_ERR (0x806e0006) </code></pre> (also, the weights json doesn&#x27;t download at all in Firefox incognito).<p>Would be good if you could pop some kind of alert (literally alert() might do the trick) on an exception just so people don&#x27;t wait for a couple of minutes before realizing something&#x27;s gone wrong :)

I released a similar web WASM transcription tool recently:<p><a href="https:&#x2F;&#x2F;bigwav.app" rel="nofollow">https:&#x2F;&#x2F;bigwav.app</a>

I need a Windows executable that takes a directory of audio files, and transcribes them to similarly named text files, so they can be searched.<p>Example: 20230406115923.mp3 ==&gt; 20230406115923.txt 20230406083110.m4a ==&gt; 20230406083110.txt<p>I wish someone would build one and sell it for $10 a copy.

Related : <a href="https:&#x2F;&#x2F;developer.mozilla.org&#x2F;en-US&#x2F;docs&#x2F;Web&#x2F;API&#x2F;Web_Speech_API" rel="nofollow">https:&#x2F;&#x2F;developer.mozilla.org&#x2F;en-US&#x2F;docs&#x2F;Web&#x2F;API&#x2F;Web_Speech_...</a>

So this is all client-side and my speech is not sent antwhere or is ut &quot;client-side ui&quot; for some API?<p>I will have a look at the repository to find out, but maybe someone already looked into it.

Very nice. Would it be easy to add other languages than English? Also, as others have notes, I had to open it in Chrome to make it work, Firefox didn&#x27;t work.

Love this idea! Tried a 10 sec clip on Firefox for Android. App seems to be stuck on <i>Transcribing...</i> for few mins now...

Wow, it worked on an iPhone despite it saying it wouldn&#x27;t work on Safari (needed Chrome).<p>The little &quot;replay your audio capture&quot; &lt;audio&gt; HTML element says &quot;error&quot; but the transcription actually worked.

This is pretty cool! Just yesterday I finished a similar demo, also using transformers.js. I am currently in the process of adding real-time transcription, do you plan on adding that?

How are you currently distributing the audio download? Any interest in using a distributed CDN layer – happy to get help get it funded

Can it identify speakers? For examples<p>SPEAKER A: blah blah<p>SPEAKER B: blah blah<p>So it can be used for transcribing phone calls?

Is there a github link? I tried clicking the logo but it didn&#x27;t work.

does not work in Firefox, but works draw-droppingly well in Chrome

So nice, it worked.<p>Is there a version of this we can run on ESP32 (arduino) devices?

Nice! Also enjoy the ffmpeg usage. Gonna give it a try!

Doesn&#x27;t seem to work in Safari

can we add a &quot;new&quot; button? I have to refresh to do it a second time

Works great, thanks

I want this but let me upload a file first.