microsoft

/

speecht5_tts

like 520

Hi! This PR has a preliminary model card, based on the format we are using as part of our effort to standardisee model cards at Hugging Face. Please see this doc of an annotated model card

Very cool! Some minor suggestions:

1. Should we put the entire abstract in the Model Description or a shortened versions? IMO we can either condense the abstract or borrow part of the introduction from @Matthijs 's blog post: https://huggingface.co/blog/speecht5#introduction

2. Missing a right bracket:

- **License:** [MIT](https://github.com/microsoft/SpeechT5/blob/main/LICENSE
+ **License:** [MIT](https://github.com/microsoft/SpeechT5/blob/main/LICENSE)

3. Missing an h:

- **Repository:** [ttps://github.com/microsoft/SpeechT5/]
+ **Repository:** [https://github.com/microsoft/SpeechT5/]

4. Since there are a lot of empty sections, could we move the empty section into markdown comments, thus condensing the model card down to the sections with just the relevant information? For example:

<!-- 
## Downstream Use [optional]

This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app

 [More Information Needed]
 -->

IMO this will make the model card easier to read!

Should we merge this?

Yes please. I would have merged it but don't appear to have the rights.

merging