Fedir Zadniprovskyi

Do you think it would be possible to give the user a choice to decide what model field `_id` gets mapped to? For example, my data already has an id...

I've had this issue when using `12.4.1-cudnn-devel-ubuntu22.04` in my `Dockerfile`, switching to `nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04` has resolved the issue for me without resorting to the `LD_LIBRARY_PATH` hackery and pip installing the drivers....

Here's a workaround, which might help for those trying to make it work in Docker. https://github.com/SYSTRAN/faster-whisper/issues/516#issuecomment-2119010765

Here's a workaround, which might help for those trying to make it work in Docker. https://github.com/SYSTRAN/faster-whisper/issues/516#issuecomment-2119010765

I've recently developed [faster-whisper-server](https://github.com/fedirz/faster-whisper-server) which provides an OpenAI compatible transcription/translation (and some extras as well) which could be used as a transcription backend if OpenWebUI adds support for having an...

@JohnSmithToYou yeah, I'll add special handling for `whisper-1`

I've recently created [faster-whisper-server](https://github.com/fedirz/faster-whisper-server), which supports `/v1/audio/transcriptions`, `/v1/audio/transcriptions`, `/v1/models`, and `/v1/models/{model}` routes, as well as streaming transcription/translation (SSE), and live audio transcription (web socket)

> I think issue is with rover always writing to System TEMP directory. https://github.com/apollographql/rover/blob/main/src/command/supergraph/compose/do_compose.rs#L133 `let dir = TempDir::new("supergraph")?;` > > Even after setting `APOLLO_HOME` and `APOLLO_CONFIG_HOME` to writable directory, rover...

Also updated the metrics example

Not very comprehensive, but please refer to [this](https://github.com/speaches-ai/speaches/blob/83981e808d118cfabef51f8dcd9adac8260fd914/docs/usage/model-discovery.md?plain=1#L73-L75). In your case, you'll need to add the following metadata to your model repository: - library_name: ctranslate2 - task_name: automatic-speech-recognition Context: https://github.com/speaches-ai/speaches/blob/83981e808d118cfabef51f8dcd9adac8260fd914/src/speaches/executors/whisper/utils.py?plain=1#L18-L26