4
votes
Speaker independent voice command recognition
CMU PocketSphinx is specifically designed to work in cases where a small set of voice commands are employed. As it uses a word-dependent phone dictionary, this would allow you to easily map different ...
- 625
3
votes
Software to create automatic subtitles (OS X)
This Python 2 script use Google Web Speech API and FFmpeg to generate subtitles: https://github.com/agermanidis/autosub
- 31
3
votes
Accepted
Android keyboard with speech-to-text that does not use Google services
Swype seems pretty awesome. It has Dragon dictation instead for voice recognition:
Swype comes with best-in-class voice recognition so you can go hands-free and dictate text quickly with a simple ...
- 146
3
votes
linux spech to text (for german)
You can use Vosk, it supports German, runs offline and can transcribe speech with Python. You can also use the speech recognition server from docker.
Latest big German model is here (1 Gb):
https://...
- 371
2
votes
MP3/WAV to text (speech recognition)
Watson's Speech to Text
This is the online demo of IBM Watson Speech to Text service. You may also use with any of SDKs available on their page. It can take a WAV file but not MP3, so you will want ...
- 338
2
votes
Open Source alternative to Wit.ai
Baidu Research released yesterday the code for its speech recognition library using Connectionist Temporal Classification implemented with Torch.
Benchmarks from Gigaom:
2
votes
Accepted
Theano-based libraries for RNN-based speech recognition
There are no plain Theano setups just because application of RNN to speech is not trivial, you need to have a good estimation before training to make the whole system converge.
CTC implementation for ...
- 371
2
votes
Android keyboard with *offline* speech-to-text that does not use Google services
TL;DR: afaik there is still no app, but open source backends now exist, so maybe it is easy to wrap it in a keyboard application I've started to build a prototype.
About 5 years ago I discovered voice ...
- 21
2
votes
Accepted
Linux Command-Line Dictation
A Python utility to cover your bases:
https://github.com/Uberi/speech_recognition
Installation pip install SpeechRecognition
Transcribing from WAV via command line: check https://github.com/Uberi/...
- 602
2
votes
On-device alternative to Android's Speech Recognition Engine?
You can use Mozilla's DeepSpeech. Some people have reported it works on Android:
https://github.com/mozilla/DeepSpeech/issues/1215
https://discourse.mozilla.org/t/offline-speech-recognition-on-mobile/...
2
votes
Speech Recognition Javascript API that recognizes standard hardcoded words via Probability
Tensorflow, the deeplearning framework by Google, is available in JavaScript. Many things can be done with it, and speech recognition is one of them.
There is a very good codelab explaining how to ...
- 216
2
votes
Accepted
Library to build a bot that can interview people over the phone
From what I can tell, you're looking at five primary components here:
The dialer, responsible for placing the initial call, and handling the other phone related aspects.
The core survey software, ...
- 1,116
2
votes
On-device alternative to Android's Speech Recognition Engine?
You could use Termux-DeepSpeech and configure Android to use that instead of the "OK Google" voice assistant. It's offline and open source since it's based on Mozilla's DeepSpeech.
Do note however, ...
- 281
2
votes
Speech Recognition: Free Software and Complete Privacy
Some list I did when asking Is there any decent speech recognition software for Linux?:
CMU Sphinx
CVoiceControl
Ears
Julius
Kaldi (e.g., Kaldi GStreamer server)
IBM ViaVoice (used to run on Linux ...
2
votes
Offline JavaScript speech recognition library
Sure, check Pocketsphinx.js a pocketsphinx port created with emscripten
To learn more about pocketsphinx check the tutorial.
- 371
1
vote
Accepted
1
vote
Customizable speech recognition
You can use Dragon NaturallySpeaking:
works on Microsoft Windows
nonfree
allows to define customize voice commands (you need the professional version for Dragon NaturallySpeaking 13 and below)
~500 ...
1
vote
Accepted
Speech Recognition: Free Software and Complete Privacy
You can try Vosk. It works on OSX with Python3.8, Windows and Linux.
Supports 9 languages - English, German, French, Spanish, Portuguese,
Chinese, Russian, Turkish, Vietnamese. More to come.
Works ...
- 371
1
vote
A software that makes subtitle for a movie?
I used to translate shows in my native language. By far the easiest one I have found is Subtitle Edit.
https://github.com/SubtitleEdit/subtitleedit/releases
Subtitle Edit is a free (open source) ...
- 1,123
1
vote
Python offline speech recognition?
You can try Kaldi, it is not easy to install, but it is more accurate than pocketsphinx. For local decoding you can use something like
https://github.com/alphacep/vosk-server/
the model is here http://...
- 371
1
vote
On-device alternative to Android's Speech Recognition Engine?
My company develops SDKs for on-device speech recognition for iOS and Android devices.
https://keenresearch.com
We have trial SDKs and couple of PoC apps on Github that you can use to evaluate the ...
- 11
1
vote
On-device alternative to Android's Speech Recognition Engine?
You can use Vosk, an open source speech recognition engine.
Android demo is here.
Supports 9 languages - English, German, French, Spanish, Portuguese,
Chinese, Russian, Turkish, Vietnamese. More to ...
- 371
1
vote
Accepted
Speech recognition software application or website for speech-to-text conversion?
https://transcribe.wreally.com/guide/how-to-transcribe-semi-automatically-using-dictation/
"supports several languages including English, Spanish, Portuguese, Dutch, Chinese, French, Hebrew, ...
- 411
1
vote
Most accurate speech recognition for high-quality audio Spanish
https://transcribe.wreally.com/guide/how-to-transcribe-semi-automatically-using-dictation/
supports several languages including English, Spanish, Portuguese, Dutch, Chinese, French, Hebrew, Italian,...
- 411
1
vote
Transcriber software for Windows?
I recommend https://transcribe.wreally.com for transcribing. You can use it with any language. You use it in the Chrome browser but you don't have to be connected to the internet while using it.
If ...
- 411
1
vote
App to help hard of hearing (HoH) for phone calls/conversations/public lectures
RogerVoice seems interesting for cell phone calls using Android phones.
http://play.google.com/store/apps/details?id=com.rogervoice.app&hl=en)
This application converts voice to text for the ...
- 1,166
1
vote
Open Source alternative to Wit.ai
Snips.ai is an alternative now (2019). Open source and privacy respecting. Their code is on github
Edit:
their console is not open source anymore since it was aquired by sonos.
- 111
1
vote
MP3/WAV to text (speech recognition)
OpenAI's Whisper (off-line, MIT license, Python 3.9, CLI) yields some highly accurate transcription. To use (tested on Ubuntu 20.04 x64 LTS but it also works on Windows):
conda create -y --name ...
1
vote
MP3/WAV to text (speech recognition)
Using Office 365 you have 300 minutes of speech recognition per month available directly in Word:
- 230
1
vote
MP3/WAV to text (speech recognition)
On Windows there's the Speech Recognition API, which is very easy to use, as in a few function calls, and you're all set.
https://msdn.microsoft.com/en-us/library/jj127860.aspx
Otherwise, albeit ...
- 131
Only top scored, non community-wiki answers of a minimum length are eligible