mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
4092fd21dc
This introduces the `YoutubeAudioLoader`, which will load blobs from a YouTube url and write them. Blobs are then parsed by `OpenAIWhisperParser()`, as show in this [PR](https://github.com/hwchase17/langchain/pull/5580), but we extend the parser to split audio such that each chuck meets the 25MB OpenAI size limit. As shown in the notebook, this enables a very simple UX: ``` # Transcribe the video to text loader = GenericLoader(YoutubeAudioLoader([url],save_dir),OpenAIWhisperParser()) docs = loader.load() ``` Tested on full set of Karpathy lecture videos: ``` # Karpathy lecture videos urls = ["https://youtu.be/VMj-3S1tku0" "https://youtu.be/PaCmpygFfXo", "https://youtu.be/TCH_1BHY58I", "https://youtu.be/P6sfmUTpUmc", "https://youtu.be/q8SA3rM6ckI", "https://youtu.be/t3YJ5hKiMQ0", "https://youtu.be/kCc8FmEb1nY"] # Directory to save audio files save_dir = "~/Downloads/YouTube" # Transcribe the videos to text loader = GenericLoader(YoutubeAudioLoader(urls,save_dir),OpenAIWhisperParser()) docs = loader.load() ``` |
||
|---|---|---|
| .. | ||
| agents | ||
| callbacks | ||
| chains | ||
| indexes | ||
| memory | ||
| models | ||
| prompts | ||
| utils/examples | ||
| agents.rst | ||
| chains.rst | ||
| indexes.rst | ||
| memory.rst | ||
| models.rst | ||
| paul_graham_essay.txt | ||
| prompts.rst | ||
| state_of_the_union.txt | ||