Open chengsokdara opened 1 year ago
when will it be created and finished react-native whisper
This looks great! Looking forward to playing around with this!
How can I help contribute to this?
There's no code to fork and make a PR from. Has the work begun here? I see several checkboxes ticked @chengsokdara
Hi sir This is Preethi I'm an engineering student and currently working on projects .I'm trying to build a app using react native .so for this purpose I need speech to text conversion using react native Can you please help with this?
I hope you can help me Thank you Yours sincerely Preethi J
On Thu, 30 Mar, 2023, 4:57 pm Tyler Sheaffer, @.***> wrote:
There's no code to fork and make a PR from. Has the work begun here? I see several checkboxes ticked @chengsokdara https://github.com/chengsokdara
— Reply to this email directly, view it on GitHub https://github.com/chengsokdara/use-whisper-native/issues/1#issuecomment-1490136178, or unsubscribe https://github.com/notifications/unsubscribe-auth/A4WPFEGD6XY3NHDX72FZAQLW6VUYPANCNFSM6AAAAAAVYDQ7MI . You are receiving this because you commented.Message ID: @.***>
Nice! Looking forward to contributing
I'd like to contribute to this. LMK where I can help out.
Did you done?
Any updates @chengsokdara ?
Eagerly waiting for this! Please give an update @chengsokdara , would really love to help.
Any update on this? @chengsokdara if you started this project but haven't had time to finish it, I'm sure you posting the work-in-progress code you did write would help others take it across the finish line! I'd happily contribut to making this a reality. Any chance you could share what you've done so far even if it's incomplete?
useWhisper Native
Dependencies
Expo version
React Native version
Tasks
[x] speech recording
[x] able to start recording
[x] able to stop recording
[x] able to pause recording
[x] able to get recorded data in chunk
[ ] speech detection
[ ] able to detect speaking start event
[ ] able to detect speaking stop event
[ ] speech transcription
[x] able to convert recorded data to base64 string
[x] send base64 data to Whisper via multipart/form-data
[ ] able to transcribe in real-time via recorded chunks
[ ] silence removal (optional)
[ ] use ffmpeg to remove silence part from recorded audio