Update README.md

README.md

@@ -8,8 +8,22 @@ language:
 - en
 base_model:
 - microsoft/wavlm-large
+datasets:
+- VCTK
+- VoxCeleb
 ---
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Library: ggmbr/wnt
-- Docs: [More Information Needed]
+# Non-timbral Embeddings extractor
+This model has been derived from the self-supervised pretrained model WavLM-large [lien]. It produces embeddings that represent the non-timbral traits (prosody, accent, ...) of a speaker, 
+which can be used the same way as for a classical ASV (automatic speaker verification) embeddings, except that only the non-timbral traits are compared.
+
+See section below for an eplanation on how to use these embeddings.
+
+# Citation
+paper
+
+# Usage
+code
+
+# Limitations
+The fine tuning data used to produce this model (VoxCeleb, VCTK) are mostly in english, which may affect the performance on other languages.