[GUIDES] Improve inference providers documentation with guides #1797
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
There was a problem hiding this comment.
looks nice, i especially like the "Your First API Call" one
cc @Wauplin @hanouticelina too
Note, i think we should showcase more and more content in JS
There was a problem hiding this comment.
hmm could we split those into another PR?
There was a problem hiding this comment.
Yeah. Makes sense.
There was a problem hiding this comment.
I opened this PR with just billing changes #1799
|
Thanks for the review @julien-c
I could add a JS version of the transcription app too. |
|
^yes! |
There was a problem hiding this comment.
Nice! very cool! love the simplicity of it, left some suggestions and more specifically a question about auto vs specific provider. Given this is tailored towards beginners or people who might not have as much insight about the ML/AI world - I tend to side with auto i.e. reduce the barrier to entry as much as possible.
|
|
||
| When prompted, paste your Hugging Face token. This handles authentication automatically for all your inference calls. You can generate one from [your settings page](https://huggingface.co/settings/tokens/new?ownUserPermissions=inference.serverless.write&tokenType=fineGrained). | ||
|
|
||
| ## Step 2: Build the User Interface |
There was a problem hiding this comment.
you can upload these as a colab notebook, so that people can just execute these as well.
There was a problem hiding this comment.
Nice idea. I'll gunna come back to this and just re-use the new model repo notebooks.
|
Thanks for the review @Vaibhavs10 . I've responded to all your comments and implemented a js version of the app. |
There was a problem hiding this comment.
this is very cool, thanks for adding these guides @burtenshaw! I left some suggestions
|
|
||
| const output = await client.automaticSpeechRecognition({ | ||
| data: file, | ||
| model: "openai/whisper-large-v3-turbo", |
There was a problem hiding this comment.
should be openai/whisper-large-v3, right?
| model: "openai/whisper-large-v3-turbo", | |
| model: "openai/whisper-large-v3", |
Thanks @hanouticelina ! I've committed your suggestions. |
|
Thanks @Vaibhavs10 @hanouticelina. All done. Could I get an approval please? |
…ithub.com/huggingface/hub-docs into improve-inference-providers-documentation
| provider: "auto" | ||
| }); | ||
|
|
||
| return output.text || output || 'Transcription completed'; |
There was a problem hiding this comment.
(nit)
return output.text ?? output ?? 'Transcription completed';
This PR is add's bite sized 'day 1' guides to the inference providers guides which should help first time users with the product:
It also includes two minor fixes: