#whisperspeech — Public Fediverse posts

#FOSDEM: Join us in the #AI devroom on Sunday as we discuss tricks learned from training large open-source #ML models on the example of #WhisperSpeech, an open-source text-to-speech model! 13:55 CEST in room ub2252a. https://fosdem.org/2025/schedule/event/fosdem-2025-6322-tricks-learned-from-training-large-open-source-models/ #OpenSource #MachineLearning

#FOSDEM: Join us in the #AI devroom on Sunday as we discuss tricks learned from training large open-source #ML models on the example of #WhisperSpeech, an open-source text-to-speech model! 13:55 CEST in room ub2252a. https://fosdem.org/2025/schedule/event/fosdem-2025-6322-tricks-learned-from-training-large-open-source-models/ #OpenSource #MachineLearning

#FOSDEM: Join us in the #AI devroom on Sunday as we discuss tricks learned from training large open-source #ML models on the example of #WhisperSpeech, an open-source text-to-speech model! 13:55 CEST in room ub2252a. https://fosdem.org/2025/schedule/event/fosdem-2025-6322-tricks-learned-from-training-large-open-source-models/ #OpenSource #MachineLearning

#FOSDEM: Join us in the #AI devroom on Sunday as we discuss tricks learned from training large open-source #ML models on the example of #WhisperSpeech, an open-source text-to-speech model! 13:55 CEST in room ub2252a. https://fosdem.org/2025/schedule/event/fosdem-2025-6322-tricks-learned-from-training-large-open-source-models/ #OpenSource #MachineLearning

#FOSDEM: Join us in the #AI devroom on Sunday as we discuss tricks learned from training large open-source #ML models on the example of #WhisperSpeech, an open-source text-to-speech model! 13:55 CEST in room ub2252a. https://fosdem.org/2025/schedule/event/fosdem-2025-6322-tricks-learned-from-training-large-open-source-models/ #OpenSource #MachineLearning

#SpeechNote 4.5.0 is now available on #Flathub!

This release is a minor update which comes with many small improvements and new #TTS, #STT and Translator models.

Highlights:
- #WhisperSpeech TTS engine and models
- Improved TTS synchronization with subtitle timestamps
- Context option for Read/Translate selected text
- New Actions and keyboard shortcuts for STT/TTS models switching

Full changelog: https://github.com/mkiol/dsnote/releases/tag/v4.5.0

Video presenting all the changes: https://youtu.be/S9MJ7y8-bcw

#SpeechNote 4.5.0 is now available on #Flathub!

This release is a minor update which comes with many small improvements and new #TTS, #STT and Translator models.

Highlights:
- #WhisperSpeech TTS engine and models
- Improved TTS synchronization with subtitle timestamps
- Context option for Read/Translate selected text
- New Actions and keyboard shortcuts for STT/TTS models switching

Full changelog: https://github.com/mkiol/dsnote/releases/tag/v4.5.0

Video presenting all the changes: https://youtu.be/S9MJ7y8-bcw

#SpeechNote 4.5.0 is now available on #Flathub!

This release is a minor update which comes with many small improvements and new #TTS, #STT and Translator models.

Highlights:
- #WhisperSpeech TTS engine and models
- Improved TTS synchronization with subtitle timestamps
- Context option for Read/Translate selected text
- New Actions and keyboard shortcuts for STT/TTS models switching

Full changelog: https://github.com/mkiol/dsnote/releases/tag/v4.5.0

Video presenting all the changes: https://youtu.be/S9MJ7y8-bcw

#SpeechNote 4.5.0 is now available on #Flathub!

This release is a minor update which comes with many small improvements and new #TTS, #STT and Translator models.

Highlights:
- #WhisperSpeech TTS engine and models
- Improved TTS synchronization with subtitle timestamps
- Context option for Read/Translate selected text
- New Actions and keyboard shortcuts for STT/TTS models switching

Full changelog: https://github.com/mkiol/dsnote/releases/tag/v4.5.0

Video presenting all the changes: https://youtu.be/S9MJ7y8-bcw

@albanobattistella BTW, In the upcoming release of SpeechNote (v4.5) you will be able to play with #WhisperSpeech models. Voice quality is very similar to 11labs but only few languages are supported (no Italian yet).

@albanobattistella BTW, In the upcoming release of SpeechNote (v4.5) you will be able to play with #WhisperSpeech models. Voice quality is very similar to 11labs but only few languages are supported (no Italian yet).

@albanobattistella BTW, In the upcoming release of SpeechNote (v4.5) you will be able to play with #WhisperSpeech models. Voice quality is very similar to 11labs but only few languages are supported (no Italian yet).

This German nonprofit is building an open voice assistant that anyone can use https://tcrn.ch/49CLkxQ via @TechCrunch

#WhisperSpeech #WhisperLive #ML #AI #TextToSpeech #OpenSource

This German nonprofit is building an open voice assistant that anyone can use https://tcrn.ch/49CLkxQ via @TechCrunch

#WhisperSpeech #WhisperLive #ML #AI #TextToSpeech #OpenSource

This German nonprofit is building an open voice assistant that anyone can use https://tcrn.ch/49CLkxQ via @TechCrunch

#WhisperSpeech #WhisperLive #ML #AI #TextToSpeech #OpenSource

This German nonprofit is building an open voice assistant that anyone can use https://tcrn.ch/49CLkxQ via @TechCrunch

#WhisperSpeech #WhisperLive #ML #AI #TextToSpeech #OpenSource

This German nonprofit is building an open voice assistant that anyone can use https://tcrn.ch/49CLkxQ via @TechCrunch

#WhisperSpeech #WhisperLive #ML #AI #TextToSpeech #OpenSource

It's time for #AIdotDev! Join us today at 3:40pm PST (UTC-8) as Jakub Piotr Cłapa presents "Tricks Learned from Scaling #WhisperSpeech Models to 80k+ Hours of Speech"! Watch the live stream here: https://www.youtube.com/watch?v=WSYSJEwOPXo #AI #ML #OpenSource

It's time for #AIdotDev! Join us today at 3:40pm PST (UTC-8) as Jakub Piotr Cłapa presents "Tricks Learned from Scaling #WhisperSpeech Models to 80k+ Hours of Speech"! Watch the live stream here: https://www.youtube.com/watch?v=WSYSJEwOPXo #AI #ML #OpenSource

It's time for #AIdotDev! Join us today at 3:40pm PST (UTC-8) as Jakub Piotr Cłapa presents "Tricks Learned from Scaling #WhisperSpeech Models to 80k+ Hours of Speech"! Watch the live stream here: https://www.youtube.com/watch?v=WSYSJEwOPXo #AI #ML #OpenSource

It's time for #AIdotDev! Join us today at 3:40pm PST (UTC-8) as Jakub Piotr Cłapa presents "Tricks Learned from Scaling #WhisperSpeech Models to 80k+ Hours of Speech"! Watch the live stream here: https://www.youtube.com/watch?v=WSYSJEwOPXo #AI #ML #OpenSource

It's time for #AIdotDev! Join us today at 3:40pm PST (UTC-8) as Jakub Piotr Cłapa presents "Tricks Learned from Scaling #WhisperSpeech Models to 80k+ Hours of Speech"! Watch the live stream here: https://www.youtube.com/watch?v=WSYSJEwOPXo #AI #ML #OpenSource

Democratizing AI just dropped a new podcast episode: "Open Source Text-To-Speech Projects: WhisperSpeech - In Depth Discussion". Tune in to unpack the evolution of #WhisperSpeech in the #OpenSource world!

➡ http://col.la/mltext #machinelearning

Democratizing AI just dropped a new podcast episode: "Open Source Text-To-Speech Projects: WhisperSpeech - In Depth Discussion". Tune in to unpack the evolution of #WhisperSpeech in the #OpenSource world!

➡ http://col.la/mltext #machinelearning

Democratizing AI just dropped a new podcast episode: "Open Source Text-To-Speech Projects: WhisperSpeech - In Depth Discussion". Tune in to unpack the evolution of #WhisperSpeech in the #OpenSource world!

➡ http://col.la/mltext #machinelearning

Democratizing AI just dropped a new podcast episode: "Open Source Text-To-Speech Projects: WhisperSpeech - In Depth Discussion". Tune in to unpack the evolution of #WhisperSpeech in the #OpenSource world!

➡ http://col.la/mltext #machinelearning

Democratizing AI just dropped a new podcast episode: "Open Source Text-To-Speech Projects: WhisperSpeech - In Depth Discussion". Tune in to unpack the evolution of #WhisperSpeech in the #OpenSource world!

➡ http://col.la/mltext #machinelearning