Speech Note

mkiol's picture
Submitted by mkiol on Mon, 2023/05/22 - 16:43
Rating: 
4.894735
Your rating: None Average: 4.9 (19 votes)

Note taking and reading with speech to text and text to speech.

Speech Note let you create and read notes using your voice. It converts speech to text and text to speech with only off-line processing. It supports many languages thanks to integration with following STT/TTS engines:  Coqui STT (Mozilla DeepSpeech), Vosk, Whisper, Piper, RHVoice, eSpeak-NG, MBROLA.

All voice analysis is entirely done locally on the device. Internet connection is only required for models download during app initial configuration. Speech Note respects your privacy and does not send any data to the Internet.

    Speech Note supports extensive number language models. Some of them give very good accuracy, but some are not perfect. All models can be downloaded directly from the app.

    A detailed list of supported languages is here.

    Limitations:

    • App does not work on i486 architecture (e.g. Jolla Tablet)
    • Models for Whisper engine are disabled on devices with ARMv7 CPU (e.g. Jolla C).
    • Models for Whisper engine are extremely slow on ARM32. Practically, they are usable only on ARM64.

    Any comments, ideas, translations, issue reports are highly appreciated.

    Translations (both Speech Note and Speech Keyboard):
    All translations are very welcome. There are three ways to contribute:
    - [preferred] Transifex project
    - Direct github pull request
    - Translation file sent to me via e-mail: dsnote@mkiol.net

    Source code: https://github.com/mkiol/dsnote
    Bugs, Feature requests: https://github.com/mkiol/dsnote/issues or just email: dsnote@mkiol.net

    Category:

    Keywords:

    Application versions: 
    AttachmentSizeDate
    File harbour-dsnote-1.5.1-1.armv7hl.rpm1.27 MB17/11/2021 - 10:00
    File harbour-dsnote-1.5.1-1.aarch64.rpm1.34 MB17/11/2021 - 19:28
    File harbour-dsnote-1.6.0-1.aarch64.rpm1.39 MB09/12/2021 - 21:32
    File harbour-dsnote-1.6.0-1.armv7hl.rpm1.31 MB09/12/2021 - 21:32
    File harbour-dsnote-1.6.1-1.armv7hl.rpm1.31 MB10/12/2021 - 20:52
    File harbour-dsnote-1.6.1-1.aarch64.rpm1.39 MB10/12/2021 - 20:52
    File harbour-dsnote-1.8.0-1.aarch64.rpm1.44 MB02/04/2022 - 19:40
    File harbour-dsnote-1.8.0-1.armv7hl.rpm1.36 MB02/04/2022 - 19:40
    File harbour-dsnote-2.0.0-1.armv7hl.rpm6.19 MB07/04/2023 - 18:03
    File harbour-dsnote-2.0.0-1.aarch64.rpm7.31 MB07/04/2023 - 18:03
    File harbour-dsnote-2.0.1-1.armv7hl.rpm6.7 MB15/04/2023 - 16:58
    File harbour-dsnote-2.0.1-1.aarch64.rpm7.86 MB15/04/2023 - 16:58
    File harbour-dsnote-3.0.0-1.aarch64.rpm92.81 MB22/05/2023 - 16:43
    File harbour-dsnote-3.0.0-1.armv7hl.rpm22.16 MB22/05/2023 - 16:43
    Changelog: 

    3.0.0

    • New feature: Note reading with Text to Speech
    • Experimental option: Restore punctuation (enabled only on ARM64)

    To read more details check About->Changes in the app.

    2.0.1

    • Translations update: Dutch, Swedish
    • Improved decoding accuracy thanks to noise canceling module.
    • Minor UI fixes

    2.0.0

    • New languages: Arabic, Bulgarian, Bosnian, Esperanto, Persian, Hindi, Japanese, Kazakh, Korean, Macedonian, Malay, Norwegian, Portuguese, Slovak, Serbian, Swedish, Swahili, Tagalog, Uzbek, Vietnamese
    • Support for Vosk engine and models
    • Support for Whisper engine and model (works decently only on ARM64)
    • New DeepSpeech models and update of existing ones
    • Voice Activity Detection
    • Option for text appending style
    • Option for setting default model (model which is used in Speech Keyboard)

    1.8.0

    • New languages: Finnish, Mongolian (experimental), Estonian (experimental)
    • Improved model for Polish language: Polski (mkiol)
    • Experimental German medical model: Deutsch (med)
    • New models for English: English (Coqui Huge Vocabulary), English (Coqui Large Vocabulary)
    • Improved languages browser
    • Support for SFOS 4.4 (sandboxing disabled)

    => I would be very grateful for any feedback how good speech transcription is for individual models.

    1.6.1

    • New German language model "Deutsch (Aashish Agarwal)" (experimental). This model might be even better than the currently configured default. I would be greateful for the feedback.

    1.6.0

    • New and default listening mode: One sentence (Clicking on the bottom panel starts listening, which ends when the first sentence is recognized)
    • Cover action (When 'One sentence' mode is set, cover displays action to enable/cancel listening.)
    • Improved language viewer
    • Coqui STT lib update (v1.1.0)
    • Bug fixes and performance improvements (e.g. App starts much quicker with multiple languages enabled)

    1.5.1

    • Fix: Languages configuration wasn't loaded when app was installed for the first time

    1.5.0

    • Fix for ARM64 - now app should work
    • Model for Catalan language
    • Many "experimental" models for various languages: Dutch, Yoruba, Amharic, Basque, Turkish, Thai, Slovenian, Romanian, Portuguese, Latvian, Indonesian, Greek, Hungarian. Most of these models provide very bad accuracy :(

    1.4.0

    • Russian and Ukrainian models
    • D-Bus API and service for 3rd-party app integration (e.g. Speech Keyboard)

    1.3.0

    • Czech language model and translation (many thanks to Lukáš Karas for the contribution)
    • New additional models: French (Common Voice), Italian (Mozilla Italia)

    1.2.0

    • Option to transcribe audio file
    • Minor UI fixes and improvements

    1.0.1

    • support for Jolla 1, Jolla C and PinePhone (alpha)
    • speech recognition accuracy is much improved thanks to DeepSpeech library update to version '0.10.0-alpha.3'
    • UI minor fixes

    Comments

    eson's picture

    eson

    Sat, 2021/10/02 - 23:00

    Well, knowing exactly nothing about the matter, I found these links on the net. Maybe you've already seen them or they are totally useless?

    https://github.com/AlexandrosFerles/Swedish-Language-Automatic-Speech-Re...

    https://github.com/se-asr/model

    https://medium.com/@klintcho/creating-an-open-speech-recognition-dataset...

     

    Thanks anyway for your good work as allways!

    mkiol's picture

    mkiol

    Mon, 2021/11/15 - 18:47

    Sorry for the late reply. Indeed this project provides model for Swedish. Unfortunately it was trained for older version of DeepSpeech and therefore it is not compatible. Sadly, there is no simple way to convert it to new one. The only solution is to repeat the training, which is possible but requires access to source material (voice samples) and significant computing power.

    defactofactotum's picture

    defactofactotum

    Sun, 2021/09/19 - 14:07

    Now working on pinephone with sfos4.2. But the microphone disconnects after every input.

    Fuchur's picture

    Fuchur

    Sat, 2021/09/04 - 21:15

    It really is working very well and a very nice app.
    One thing I really would love to see is to be have a button on the keyboard or an own keyboard layout which would include it to the keyboard input.

    That would just be great :).

    lispy's picture

    lispy

    Fri, 2021/06/04 - 20:12

    Really works. I like it. My wife has to convert a huge audiofile to text but pushing the button for an hour sadly doesn't cut it for her. Can you imagine an audiofile import of sorts? Or maybe make the button sticky?

    mkiol's picture

    mkiol

    Sat, 2021/09/18 - 20:38

    There are to modes (Settings->"Speech detection mode"). In "Automatic" mode, you don't have to hold the button. App will (in most cases ;-) automaticaly detect that speaking begins.

    defactofactotum's picture

    defactofactotum

    Mon, 2021/05/03 - 14:51

    Thanks for the keyboard fix! It still doesn't work on my pinephone - it worked briefly in Italian but with very bad recognition, then stopped again. Another suggestion: would it be possible to add words to the database? I imagine this is probably a huge and complicated task....

    defactofactotum's picture

    defactofactotum

    Tue, 2021/04/27 - 11:22

    Also does not work on pinephone. Suggestion for keyboard behaviour: at the moment it's possible to edit text in the middle of a line but after typing one letter the cursor snaps back to end of line. When an entire word is wrong this is very laborious.

    mkiol's picture

    mkiol

    Thu, 2021/04/29 - 11:33

    Thank for suggestion.

    In the meantime, I've managed to fix Jolla 1, Jolla C and PinePhone issue. Moreover with alpha version of DeepSpeech accuracy of recognition is much improved. Stay tuned for next release :)

    ichthyosaurus's picture

    ichthyosaurus

    Fri, 2021/04/23 - 21:20

    This looks very promising - I suggest that you ask for it to be included in the next community news :)!

    mkiol's picture

    mkiol

    Fri, 2021/04/23 - 20:14

    Unfortunately app does not work on Jolla C (and most likely on other older devices). Sorry :(

    sashikknox's picture

    sashikknox

    Fri, 2021/04/23 - 13:42

    Cool, start testing... Too long time while download soeech model

    mkiol's picture

    mkiol

    Fri, 2021/04/23 - 20:10

    Indeed, download time might be long. Model size for english is almost 1GB.

    Pelzlurch's picture

    Pelzlurch

    Fri, 2021/04/23 - 10:07

    For a first version indeed quite polished. Recognition quality is not brillant but quite OK - and very cool - offline!
    The only thing I noticed negatively is that there is no automatic line break.

    defactofactotum's picture

    defactofactotum

    Fri, 2021/04/23 - 13:29

    Thanks for this! I haven't tried it much except for simple phrases but seems to work well. Maybe in the future you could make it easier to copy lines of text to other apps.

    oops just noticed now you can copy text on the pulley menu!
     I dictated this with speech note....

    mkiol's picture

    mkiol

    Fri, 2021/04/23 - 20:11

    nice :D

    ziellos's picture

    ziellos

    Thu, 2021/04/22 - 23:31

    Thanks a lot! Had no chance to really test speech recognition, but your app looks already very polished.

    Pages