Speech Note 4.1.0

Linux Desktop

Changes:

• Speech to Text:
  • Support for GPU acceleration for Whisper models
  • Fix: Whisper wasn't able to decode short speech sentences
• Text to Speech:
  • Option 'Speech speed' to make synthesized speech slower or faster.
  • New models from Massively Multilingual Speech (MMS) project:
    Albanian, Amharic, Arabic, Basque, Bengali, Bulgarian, Chinese,
    Greek, Hindi, Icelandic, Indonesian, Kazakh, Korean, Latin,
    Latvian, Malay, Mongolian, Polish, Portuguese, Swahili, Tagalog,
    Tatar, Thai, Turkish, Uzbek, Vietnamese, Yoruba
  • New Piper voices: Czech, German, Hungarian, Portuguese, Slovak,
    English
  • Update of RHVoice voices for Slovak and Czech
  • New Coqui voices for Japanese, Turkish and Spanish
  • Fix: Splitting text into sentences was incorrect for: Georgian,
    Japanese, Bengali, Nepali, Hindi
• Interface
  • Option to change font size in text editor

Sailfish OS

Changes:

• Speech to Text:
  • Remove of experimental 'Restore punctuation' option
  • Fix: Whisper wasn't able to decode short speech sentences
• Text to Speech:
  • Option 'Speech speed' to make synthesized speech slower or faster.
  • New Piper voices: Czech, German, Hungarian, Portuguese, Slovak,
    English
  • Update of RHVoice voices for Slovak and Czech
  • Fix: Splitting text into sentences was incorrect for: Georgian,
    Japanese, Bengali, Nepali, Hindi

Speech Note 4.0.0

Changes:

• Translator:
  • Support for offline translations.
• Interface:
  • User interface redesign
  • Settings option to force specific interface style.
  • App translated to new languages: Dutch and Italian
• Text to Speech:
  • All existing Piper models were updated.
  • New Piper voices for: English, Swedish, Turkish, Polish,
    German, Spanish, Finnish, French, Ukrainian, Russian,
    Swahili, Serbian, Romanian, Luxembourgish and Georgian
  • New RHVoice model for Slovak language

Speech Note 3.1.5

Changes in Linux Desktop version:

• Text to Speech:
  • New Coqui voice for English: Jenny
• Speech to Text:
  • Quicker decoding when using DeepSpeech/Coqui models (especially on ARM CPU)

Changes in Sailfish OS version:

• Speech to Text:
  • Quicker decoding when using DeepSpeech/Coqui models
  • Re-enabled Swedish Vosk model

Speech Note 3.1.4

Changes in Linux Desktop version:

• Interface:
  • Option to show recent changes (About -> Changes)
  • French translation update (Many thanks to @LAfricain)
• Text to Speech:
  • New Piper model for Chinese
  • New RHVoice model for Uzbek (Beta)
  • Updated RHVoice models for Ukrainian
  • Piper and RHVoice engines updated to most recent versions
• Speech to Text:
  • Whisper 'Large' models enabled for all languages
  • Whisper supported on older CPUs (i.e. without AVX/AVX2 extensions)
  • Whisper engine update (20% performance improvement, 50% less memory)

Changes in Sailfish OS version:

• Interface:
  • French translation update (Many thanks to @LAfricain)
• Text to Speech:
  • New Piper model for Chinese
  • New RHVoice model for Uzbek (Beta)
  • Updated RHVoice models for Ukrainian
  • Piper and RHVoice engines updated to most recent versions
• Speech to Text:
  • Whisper 'Small' models enabled for all languages
  • Whisper fine-tuned 'Small' models for: Croatian, Czech, Hungarian, Slovak and Romanian
  • Whisper engine update (test on Xperia 10 III: 20% performance improvement, 50% less memory)

Speech Note 3.1.3

Changes:

• New Piper Text-to-Speech models for: Icelandic, Swedish, Russian
• Whisper 'fine-tuned' Speech-To-Text models for: Czech, Slovak, Slovenian, Romanian, Russian, Hungarian, Polish
• Whisper models enabled also for: Amharic, Arabic, Bengali, Danish, Estonian, Basque, Persian, Hindi, Croatian, Hungarian, Icelandic, Georgian, Kazakh, Korean, Lithuanian, Latvian, Mongolian, Maltese, Nepali, Romanian, Slovak, Slovenian, Albanian, Swahili, Tagalog, Tatar, Uzbek, Yoruba

Speech Note 3.1.1

Changes:

• Option to save speech to audio file
• New STT DeepSpeech model for Latvian language
• Linux Desktop UI (Flatpak release on flathub.org)
• Coqui TTS models for many languages (only in x86_64 Flatpak version)

Speech Note 3.0.0

Changes:

• Note reading with Text to Speech
• Restore punctuation option

Speech Note 2.0.1

Changes:

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

Speech Note 2.0.0

Changes:

• 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)

Speech Note 1.8.0

Changes:

• 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