vikarti.anatra/AudioSumma
1
0
Fork 0
mirror of https://github.com/patw/AudioSumma.git synced 2025-09-01 10:09:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
35 commits 1 branch 0 tags 152 KiB
Commit graph

35 commits

This branch
This branch
All branches
Author SHA1 Message Date
Pat Wendorf
9b8a6077bf Switched bytes to tokens to be consistent with output. Allowed much larger outputs and inputs to support long context models. 2025-07-02 12:50:24 -04:00
Pat Wendorf
6e2fa21b62 Removed temp and top_p, that should be controlled by the hosted model now. 2025-05-13 08:38:31 -04:00
Pat Wendorf (aider)
aec8919bf6 fix: join paths when deleting files in clean() 2025-05-09 11:35:35 -04:00
Pat Wendorf (aider)
a2a3f900d2 fix: join output dir path when opening transcript files 2025-05-09 11:34:23 -04:00
Pat Wendorf (aider)
eca331e773 fix: use full path when checking for existing transcripts 2025-05-09 11:31:16 -04:00
Pat Wendorf (aider)
d9de639553 fix: use full paths for wav file operations 2025-05-09 11:26:45 -04:00
Pat Wendorf
23d2e3715c Line spacing in config dialog was too much 2025-05-09 10:56:04 -04:00
Pat Wendorf (aider)
60215cc0c4 feat: add configurable output directory for transcripts 2025-05-09 10:51:15 -04:00
Pat Wendorf
b90b651f14 Forgot the v1 endpoint for llama.cpp/ollama 2025-05-09 10:49:11 -04:00
Pat Wendorf (aider)
b754738146 feat: replace input fields with text areas in config dialog 2025-05-09 10:48:22 -04:00
Pat Wendorf (aider)
73279657da feat: increase settings dialog size and field heights 2025-05-09 10:46:00 -04:00
Pat Wendorf
f1fb9f0a2b Removed the old sample.env file and updated readme. 2025-05-09 10:44:52 -04:00
Pat Wendorf
80101d577c More refined prompts 2025-05-09 10:41:49 -04:00
Pat Wendorf
150d910ddb more better defaults 2025-05-09 10:15:47 -04:00
Pat Wendorf
40de47afe2 More reasonable defaults from the working system 2025-05-09 10:07:29 -04:00
Pat Wendorf (aider)
08b2a2b627 feat: add config dialog and move settings from .env to config.json 2025-05-09 09:55:03 -04:00
Pat Wendorf (aider)
b9963599e3 docs: add macOS homebrew requirements to README 2025-05-09 09:47:16 -04:00
Pat Wendorf
2fe4893296 After merging summarize into meetings removed meetings.py 2025-05-09 09:37:26 -04:00
Pat Wendorf (aider)
04659ed489 refactor: merge summarize.py functionality into meetings.py 2025-05-09 09:30:36 -04:00
Pat Wendorf
b9533bf503 Sample env was missing the fact prompt 2025-02-20 19:18:15 -05:00
Pat Wendorf
70a8816e8b Forgot to update sample file. 2025-02-08 08:54:58 -05:00
Pat Wendorf
c947e08cdc Allow for adjustment of temp, top_p and max tokens for models that have issues with repeating. 2025-02-08 08:54:29 -05:00
Pat Wendorf
933b9e24d4 Skip transcribe step if it's already done. Show each part being summarized. 2025-02-03 16:30:52 -05:00
Pat Wendorf
2d329d4806 Updated instructions for new .env settings 2024-11-29 09:08:24 -05:00
Pat Wendorf
80637cc26c Simplified the transcriber by using the openai library to access llama.cpp server or ollama server mode. 2024-11-29 09:06:22 -05:00
Pat Wendorf
77b7f440a0 Replaced the screenshot to show the new recording device selector 2024-08-19 08:33:29 -04:00
Pat Wendorf
6128f02615 Added drop down for selecting the recording device. 2024-08-19 08:32:24 -04:00
Pat Wendorf
ac27eaf826 Treat the summarizer as a module now, and call it with threading instead of subprocess 2024-08-19 07:55:46 -04:00
Pat Wendorf
3c05cd78dd Used mistral large to re-write the summarize process. 2024-08-19 07:41:32 -04:00
Pat Wendorf
81e4e165bc Added some silence trimming 2024-07-30 11:56:40 -04:00
Pat Wendorf
f5af4960fc Extract some fact based summaries now as well 2024-06-24 09:52:38 -04:00
Pat Wendorf
cb00762378 UI looks a bit better now 2024-06-24 09:38:54 -04:00
Pat Wendorf
fe50d40fce Mention you need llama.cpp and whisper.cpp running in server mode 2024-06-21 12:56:41 -04:00
Pat Wendorf
f8c7d09a59 Accidentally removed MD files 2024-06-21 12:53:08 -04:00
Pat Wendorf
69d269d2f0 first commit 2024-06-21 12:52:10 -04:00