From e3a9730f3ce5f2b0033d19489fc83ecfd3f626bd Mon Sep 17 00:00:00 2001 From: Robert Date: Sat, 4 May 2024 20:30:54 -0700 Subject: [PATCH] Updated requirements.txt & README.md --- README.md | 15 +++++++++++++-- requirements.txt | Bin 4526 -> 4988 bytes 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index bc3263a48..4458f786e 100644 --- a/README.md +++ b/README.md @@ -2,10 +2,12 @@ Take a URL, single video, list of URLs, or list of local videos + URLs and feed it into the script and have each video transcribed (and downloaded if not local) using faster-whisper. Transcriptions can then be shuffled off to an LLM API endpoint of your choice, whether that be local or remote. Any site supported by yt-dl is supported, so you can use this with sites besides just youtube. +I personally recommend Sonnet, for the price it's very nice. + Original: `YouTube contains an incredible amount of knowledge, much of which is locked inside multi-hour videos. Let's extract and summarize it with AI!` ### tl/dr: Download Videos -> Transcribe -> Summarize. Scripted. -- Use the script to transcribe a local file or remote url. Any url youtube-dl supports _should_ work. If you pass an OpenAPI endpoint as a second argument, and add your API key to the config file, you can have your resulting transcriptions summarized as well. +- Use the script to transcribe a local file or remote url. Any url youtube-dl supports _should_ work. If you pass an API name (openai/anthropic/cohere) as a second argument, and add your API key to the config file, you can have your resulting transcriptions summarized as well. * The current approach to summarization is currently 'dumb'/naive, and will likely be replaced or additional functionality added to reflect actual practices and not just 'dump txt in and get an answer' approach. Save time and use the `config.txt` file, it allows you to set these settings and have them used when ran. @@ -19,13 +21,22 @@ positional arguments: options: -h, --help show this help message and exit - --api_url API_URL API URL for summarization (optional) + --api_name API_NAME API name for summarization (optional) + --api_key API_KEY API key for summarization (optional) --num_speakers NUM_SPEAKERS Number of speakers (default: 2) --whisper_model WHISPER_MODEL Whisper model (default: small.en) --offset OFFSET Offset in seconds (default: 0) --vad_filter Enable VAD filter + --log_level {DEBUG,INFO,WARNING,ERROR,CRITICAL} + Log level (default: INFO) + +>python diarize.py ./local/file_on_your/system --api_name anthropic +>python diarize.py https://www.youtube.com/watch?v=4nd1CDZP21s --api_name anthropic +>python diarize.py https://www.youtube.com/watch?v=4nd1CDZP21s --api_name openai +>python diarize.py https://www.youtube.com/watch?v=4nd1CDZP21s --api_name anthropic --api_key lolyearight +>python diarize.py https://www.youtube.com/watch?v=4nd1CDZP21s --api_name openai --api_key lolyearight ``` diff --git a/requirements.txt b/requirements.txt index 3db47549dd86419779df3d5c76537a12e1eed10b..5fcad5c35cb6af25e1c99231590a64055a27fc0a 100644 GIT binary patch delta 431 zcmYjN%}T>y5L^=sSR;vw_=6%e{y>YRU(#AVcvXCXdJqLErY+c75-Zxbkj0xIh-XD| z5b+?siuev9h;=qGBFncS%?*^(!1#)RU?!tS} z_I2**S+43ce5FqfdVosNrT(gM&&ctnu@K!FS$#63E<~CT6qzzuBC-~}3~djLcjz4Y ziGv~qKyg3w>@?_@+O$GGszn_z>hZV>h9pts^8N7RTph^SFH%H42>}e