31

Is there a Ubuntu alternative for this program?

| improve this question | | | | |
  • Do you care if is FOSS? Should work offline? Only for English usage? – Pablo Bianchi Dec 27 '18 at 22:54
18

There is a whole Article on Wikipedia dedicated to the Problem.

Unfortunately, it seems there's currently no one solution that works well enough, but a massive list of projects that are underway.

You may want to rummage through the list of solutions to see if there's anything that fits your needs.

Platypus:

There's always the possibility to run Dragon Naturally Speaking using WINE. The Platypus Project is creating software to redirect Dragon's output to any Linux / X application, and they are very far along.

You should definitely take a look at this.

| improve this answer | | | | |
5
+150

For an updated answer, here is an article from March 2018: Best Free Linux Speech Recognition Tools – Open Source Software.

This article highlights the best open source speech recognition software for Linux. Note, some of the software is in an early state of development, and is therefore not ready for widespread adoption.

Before examining our recommendations, Jasper is worthy of a special mention. It’s an excellent open source platform for developing always-on, voice-controlled applications. You may be wondering why HTK doesn’t appear below. For sure, HTK is a popular speech recognition toolkit. But HTK is not eligible to feature in the recommended solutions. Not because it’s copyright is owned by Microsoft, but simply because it’s proprietary software.

Let’s explore the 6 free speech recognition tools at hand. For each title we have compiled its own portal page with a full description and an in-depth analysis of its features.

Open Source Speech Recognition Tools

  • DeepSpeech TensorFlow implementation of Baidu's DeepSpeech architecture.
  • Julius Two-pass large vocabulary continuous speech recognition engine
  • Simon Flexible speech recognition software
  • CMUSphinx Speech recognition system for mobile and server applications
  • deepspeech.pytorch Implementation of DeepSpeech2 using Baidu Warp-CTC.
  • Kaldi C++ toolkit designed for speech recognition researchers.
| improve this answer | | | | |
4

You can install Chromium 11 version from the ppa ppa:chromium-daily/stable (How to add an PPA) and add --enable-speech-input to the end of the launcher.

enter image description here

Now visit this website and whoo! Speech-to-Text on ubuntu using html5.

I read here that if you speak slowly it will be more accurate.

enter image description here

| improve this answer | | | | |
3

freespeech-vr

Is a decent open source speech to text engine. Here the source code (on Google Code)

Note that it takes a bit of configuration, which is less polished than Dragon Naturally Speaking's configuration.

| improve this answer | | | | |
  • 2
    FreeSpeech appears not to be maintained. It hasn't offered a ppa since Ubuntu 10. – JellicleCat Feb 20 '15 at 18:57
  • 2
    There is now a Python 3 port of FreeSpeech. – dotancohen Dec 31 '17 at 8:49
1

Dictanote

To expand on Alaukik's answer, there are apps built on top of Chrome speech recognition capabilities.

I personally use Dictanote (it is very similar to Dragon). Here is a link to chrome app.

| improve this answer | | | | |
1

Try Mozilla DeepSpeech an opensource tool for automatic transcription. But you will need to train the tool or download Mozilla's pre-trained model. For very clear recordings, the accuracy rate is relatively good. but for my projects, it was still not sufficient, as the recordings had lots of background noises, they were not of good quality, I used Transcribear instead, it's web based editor that allows for automatic transcription, but you will need to be connected online to upload recordings to the Transcribear server.

| improve this answer | | | | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.