transcribe
transcribe copied to clipboard
Transcribe is a real time transcription, conversation, Language learning platform. It provides live transcripts from microphone and speaker. It generates a suggested conversation response using OpenAI...
### Discussed in https://github.com/vivekuppal/transcribe/discussions/193 Originally posted by **tan-banana** April 4, 2024 Plus support for context model api that can continually be updated per conversation having both a short and long...
User should be able to choose different content strings on the left side and any corresponding responses from LLM should be displayed on the right side again.
### Discussed in https://github.com/vivekuppal/transcribe/discussions/192 Originally posted by **tan-banana** April 4, 2024 similar to how open ai's backend has the option to edit context and other model variables. Say I get...
After running properly for several times, an LLM error occurs, resulting in no reply displayed on the right. I do not know whether the agent is affected. Can you solve...
Error when attempting to get a response from LLM. list index out of range Exception in thread AudioResponse: Traceback (most recent call last): File "C:\Transcribe-main\transcribe-main\env\Lib\site-packages\urllib3\connection.py", line 198, in _new_conn sock...
How can we go about setting up 'context' for the LLM to respond based on? For example, I would like to feed it information about myself and get responses tailored...
Currently the response language of LLM can be set in the parameters.yaml. Allow user to set the language using UI. Users choice should be persisted across restarts of the application.
- Add shortcut keys to start/pause/stop the transcriptions - Even for "continuous response" and others shortcut keys can be added This convenience makes it more easy to navigate across the...
Hi there, I am the author of static-ffmpeg. I humbly request you use this library (ffmpeg v5) so that you can skip the ffmpeg install step. https://github.com/zackees/static_ffmpeg
I felt like if there is an option to edit the text what the speaker said would be a good feature. sometimes it is unable to transcribe some words properly....