Sidharth Rajaram

Issue: Very long runtimes for RetrievalQA chain with GPT4All

2

### RetrievalQA chain with GPT4All takes an extremely long time to run (doesn't end) I encounter massive runtimes when [running a RetrievalQA chain](https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa.html) with a locally downloaded GPT4All LLM. Unsure...

Downloading and caching ability when loading checkpoints (similar to Transformers API). - Can now provide a checkpoint filename or a checkpoint URL (or just a file path as before). Regardless,...

## ❓ Questions and Help ### Before asking: - [x] search the issues. - [x] search the docs. #### What is your question? I have extended FairseqDataset and created a...

Optional dependencies for GCS/S3/HuggingFace-Hub?

1

Hi, big fan of the project! `cached_path` is certainly very capable because of the support for GCS/S3/HuggingFace out of the box, but one issue is that it seems to bring...

Plans to support Parler TTS on Candle?

5

Hello, are there plans to support Parler-TTS on Candle? Thanks!

Hi, big fan of the project. Transcription and diarization works pretty great from CLI. Is there a way to perform speaker diarization without CLI?