Upload README.md with huggingface_hub

README.md

@@ -22,15 +22,15 @@ tags:
 This is a Natural Language Understanding (NLU) model for the French [MEDIA benchmark](https://catalogue.elra.info/en-us/repository/browse/ELRA-S0272/).
 It maps each input words into outputs concepts tags (76 available).
 
-This model is trained using [`nherve/flaubert-oral-mixed`](https://huggingface.co/nherve/flaubert-oral-mixed) as its inital checkpoint.
+This model is trained using [`nherve/flaubert-oral-mixed`](https://huggingface.co/nherve/flaubert-oral-mixed) as its inital checkpoint. It obtained 12.47% CER in the MEDIA test set, in [our Interspeech 2023 publication](http://doi.org/10.21437/Interspeech.2022-352).
 
 ## Available MEDIA NLU models:
-- [`vpelloin/MEDIA_NLU-flaubert_base_cased`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_base_cased): MEDIA NLU model trained using [`flaubert/flaubert_base_cased`](https://huggingface.co/flaubert/flaubert_base_cased)
-- [`vpelloin/MEDIA_NLU-flaubert_base_uncased`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_base_uncased): MEDIA NLU model trained using [`flaubert/flaubert_base_uncased`](https://huggingface.co/flaubert/flaubert_base_uncased)
-- [`vpelloin/MEDIA_NLU-flaubert_oral_ft`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_oral_ft): MEDIA NLU model trained using [`nherve/flaubert-oral-ft`](https://huggingface.co/nherve/flaubert-oral-ft)
-- [`vpelloin/MEDIA_NLU-flaubert_oral_mixed`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_oral_mixed): MEDIA NLU model trained using [`nherve/flaubert-oral-mixed`](https://huggingface.co/nherve/flaubert-oral-mixed)
-- [`vpelloin/MEDIA_NLU-flaubert_oral_asr`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_oral_asr): MEDIA NLU model trained using [`nherve/flaubert-oral-asr`](https://huggingface.co/nherve/flaubert-oral-asr)
-- [`vpelloin/MEDIA_NLU-flaubert_oral_asr_nb`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_oral_asr_nb): MEDIA NLU model trained using [`nherve/flaubert-oral-asr_nb`](https://huggingface.co/nherve/flaubert-oral-asr_nb)
+- [`vpelloin/MEDIA_NLU-flaubert_base_cased`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_base_cased): MEDIA NLU model trained using [`flaubert/flaubert_base_cased`](https://huggingface.co/flaubert/flaubert_base_cased). Obtains 13.20% CER on MEDIA test.
+- [`vpelloin/MEDIA_NLU-flaubert_base_uncased`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_base_uncased): MEDIA NLU model trained using [`flaubert/flaubert_base_uncased`](https://huggingface.co/flaubert/flaubert_base_uncased). Obtains 12.40% CER on MEDIA test.
+- [`vpelloin/MEDIA_NLU-flaubert_oral_ft`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_oral_ft): MEDIA NLU model trained using [`nherve/flaubert-oral-ft`](https://huggingface.co/nherve/flaubert-oral-ft). Obtains 11.98% CER on MEDIA test.
+- [`vpelloin/MEDIA_NLU-flaubert_oral_mixed`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_oral_mixed): MEDIA NLU model trained using [`nherve/flaubert-oral-mixed`](https://huggingface.co/nherve/flaubert-oral-mixed). Obtains 12.47% CER on MEDIA test.
+- [`vpelloin/MEDIA_NLU-flaubert_oral_asr`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_oral_asr): MEDIA NLU model trained using [`nherve/flaubert-oral-asr`](https://huggingface.co/nherve/flaubert-oral-asr). Obtains 12.43% CER on MEDIA test.
+- [`vpelloin/MEDIA_NLU-flaubert_oral_asr_nb`](https://huggingface.co/vpelloin/MEDIA_NLU-flaubert_oral_asr_nb): MEDIA NLU model trained using [`nherve/flaubert-oral-asr_nb`](https://huggingface.co/nherve/flaubert-oral-asr_nb). Obtains 12.24% CER on MEDIA test.
 
 ## Usage with Pipeline
 ```python