CODE

→ View original post on X — @reach_vb

Open Source Speech Synthesis Models: FastSpeech2, VITS, TorToise

By

@reach_vb

–

10 February 2023 21h22

Yes! My point was referring specific to closed source API the David was mentioning in the video.
All, FastSpeech2, VITS and TorToise (inference) are OSS. :))

→ View original post on X — @steipete

Automate multilingual string updates with Pull Requests

By

@steipete

–

10 February 2023 21h05

Yeah you don‘t wanna coordinate any of that. You want someone that sees that you checked in new english strings into your localized.strings file and sends a Pull Request with the other languages.

Documentation Updates and Bug Fixes Released

By

–

10 February 2023 20h57

And of course, lots of usual docs/bug fixes! s/o @eltociear @tangjeff0 (x2) @concaption @kevin_w_huo Jon Luo, Peng Qu Happy weekend!

LangChain Adds Batch Embeddings Support for OpenAI

By

–

10 February 2023 20h57

Batch embeddings While we have support for batch processing of LLM calls, we didn't have support for batch processing of embeddings until now. @jmdagdelen added it for the @OpenAI embedding module PR: https://
github.com/hwchase17/lang
chain/pull/969/files
…

LangChain PagedPDF Tracks Page Numbers for Source Citations

By

–

10 February 2023 20h57

PDFs with pages @andrewwhite01 added a PagedPDF that keeps track of page numbers in the metadata This metadata is useful when doing question answering with sources! Docs: https://
langchain.readthedocs.io/en/latest/modu
les/document_loaders/examples/pdf.html
…

LangChain YouTube Metadata Integration Feature

By

–

10 February 2023 20h57

YouTube metadata Speaking of metadata, thanks to Alex Zhangji you can now specify `add_video_info=True` and it will add relevant metadata from YouTube to the document Docs: https://
langchain.readthedocs.io/en/latest/modu
les/document_loaders/examples/youtube.html#add-video-info
…