TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: Best speech-to-text resource?

22 pointsby jamesandthewolfover 3 years ago
Anyone know any good speech to text resources Ive tried a few but they keep not writing down the correct words looking more free and open source links.<p>I have terrible spelling and grammar as I suffer from Dyslexia and the speech to text kind of helps me. I can write but it&#x27;s harder for myself then speaking. I can read ok my the spelling part is difficult as I mix words and letters up and spend most of my time just checking and rewriting large portions of my narratives.

8 comments

woodsonover 3 years ago
If you&#x27;re fine writing code to build a solution yourself, try the Conformer or ContextNet models in Nvidia NeMo (<a href="https:&#x2F;&#x2F;docs.nvidia.com&#x2F;deeplearning&#x2F;nemo&#x2F;user-guide&#x2F;docs&#x2F;en&#x2F;stable&#x2F;starthere&#x2F;intro.html" rel="nofollow">https:&#x2F;&#x2F;docs.nvidia.com&#x2F;deeplearning&#x2F;nemo&#x2F;user-guide&#x2F;docs&#x2F;en...</a>) or Vosk (<a href="https:&#x2F;&#x2F;alphacephei.com&#x2F;vosk&#x2F;" rel="nofollow">https:&#x2F;&#x2F;alphacephei.com&#x2F;vosk&#x2F;</a>), which nicely packages an API for Kaldi chain&#x2F;LF-MMI models.
GhettoComputersover 3 years ago
Is it only English? I used this and it’s amazing. Google live transcribe is great!<p><a href="https:&#x2F;&#x2F;play.google.com&#x2F;store&#x2F;apps&#x2F;details?id=com.google.audio.hearing.visualization.accessibility.scribe" rel="nofollow">https:&#x2F;&#x2F;play.google.com&#x2F;store&#x2F;apps&#x2F;details?id=com.google.aud...</a>
jlalfonso21over 3 years ago
If you can code or know how to use some demos, you can give a try to Vosk, this is a opensource project with multiple implementations and language models, opensource as well, all of this offline. They have smalls and big models, for mobile apps, iot, asterisk, and much more<p><a href="https:&#x2F;&#x2F;alphacephei.com&#x2F;vosk&#x2F;" rel="nofollow">https:&#x2F;&#x2F;alphacephei.com&#x2F;vosk&#x2F;</a>
runnerupover 3 years ago
<a href="https:&#x2F;&#x2F;www.rev.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.rev.ai&#x2F;</a> beats Google&#x27;s speech-to-text models quite impressively.
Cilvicover 3 years ago
<a href="https:&#x2F;&#x2F;github.com&#x2F;coqui-ai&#x2F;STT" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;coqui-ai&#x2F;STT</a>
geenatover 3 years ago
If it&#x27;s really important to you, latest pixel phone honestly. Google has an excellent implementation here.
评论 #29114600 未加载
innerzealover 3 years ago
Otter.ai is pretty good and free mins are available.
jamesandthewolfover 3 years ago
Thanks I&#x27;ll check these out