blob42/langchain
1
0
Fork 0
forked from Archives/langchain
Code Issues Pull Requests Packages Projects Releases Wiki Activity
137da7e4b6
langchain/tests/unit_tests/document_loaders/blob_loaders
History
Lance Martin 4092fd21dc
YoutubeAudioLoader and updates to OpenAIWhisperParser (#5772) 
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()
```
2023-06-06 15:15:08 -07:00
..
__init__.py fix(document_loaders/telegram): fix pandas calls + add tests (#4806) 2023-05-16 14:35:25 -07:00
test_filesystem_blob_loader.py fix(document_loaders/telegram): fix pandas calls + add tests (#4806) 2023-05-16 14:35:25 -07:00
test_public_api.py YoutubeAudioLoader and updates to OpenAIWhisperParser (#5772) 2023-06-06 15:15:08 -07:00
test_schema.py fix: Blob.from_data mimetype is lost (#5395) 2023-05-29 06:36:50 -07:00