Add library name, pipeline tag, link to paper and Github repo

This PR improves the model card by adding:
- the `library_name` to facilitate usage of the model
- a more relevant `pipeline_tag`
- a link to the paper
- the Github repo

README.md

@@ -1,13 +1,13 @@
 ---
-license: cc-by-4.0
-language:
-- en
-- it
 datasets:
 - FBK-MT/mosel
 - facebook/covost2
 - openslr/librispeech_asr
 - facebook/voxpopuli
+language:
+- en
+- it
+license: cc-by-4.0
 metrics:
 - comet
 - wer
@@ -17,6 +17,8 @@ tags:
 - speech translation
 - ASR
 - ST
+pipeline_tag: automatic-speech-recognition
+library_name: transformers
 ---
 
 # FAMA-medium
@@ -43,6 +45,7 @@ All the artifacts used for realizing FAMA models, including codebase, datasets,
 themself are [released under OS-compliant licenses](#license), promoting a more
 responsible creation of models in our community.
 
+For further details, please refer to the paper [FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian](https://huggingface.co/papers/2505.22759).
 
 It is available in 2 sizes, with 2 variants for ASR only:
 
@@ -52,6 +55,7 @@ It is available in 2 sizes, with 2 variants for ASR only:
 - [FAMA-medium-asr](https://huggingface.co/FBK-MT/fama-medium-asr) - 878 million parameters
 
 For more information about FAMA, please check our [blog post](https://huggingface.co/blog/FAMA/release) and the [arXiv](https://arxiv.org/abs/2505.22759) preprint.
+Code can be found at: https://github.com/hlt-mt/FBK-fairseq
 
 ## Usage