You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe:
Is it possible to run speech recognition completely offline?
Describe the solution you'd like:
I have an app usecase where it will be used in remote areas where not even an internet mobile data works. need to still speak out to the app, have the speech recognition working to capture what has been said, and store the transcribed text after getting internet connection again. At the moment it seems like speech recognition can only work when theres active internet connection. when i turn off internet, it just make a beep sound that indicate refusal to accept speech.
Describe alternatives you've considered:
Similar approach would be using AI whisper technology, where the model is stored offline.. and the audio spoken via mic is captured (perhaps using webRTC), and the recorded audio is crossmatched with AI model to get transcription
The text was updated successfully, but these errors were encountered:
Is your feature request related to a problem? Please describe:
Is it possible to run speech recognition completely offline?
Describe the solution you'd like:
I have an app usecase where it will be used in remote areas where not even an internet mobile data works. need to still speak out to the app, have the speech recognition working to capture what has been said, and store the transcribed text after getting internet connection again. At the moment it seems like speech recognition can only work when theres active internet connection. when i turn off internet, it just make a beep sound that indicate refusal to accept speech.
Describe alternatives you've considered:
Similar approach would be using AI whisper technology, where the model is stored offline.. and the audio spoken via mic is captured (perhaps using webRTC), and the recorded audio is crossmatched with AI model to get transcription
The text was updated successfully, but these errors were encountered: