Update README.md

README.md

@@ -1,3 +1,40 @@
----
-license: cc-by-nc-sa-4.0
----
+---
+license: cc-by-nc-sa-4.0
+language:
+- en
+pipeline_tag: audio-classification
+tags:
+- wavlm
+- wav2vec2
+- msp-podcast
+- emotion-recognition
+- audio
+- speech
+- valence
+- arousal
+- dominance
+- speech-emotion-recognition
+- dkounadis
+---
+Tecaher model based on [wavlm](https://huggingface.co/3loi/SER-Odyssey-Baseline-WavLM-Multi-Attributes) and [wav2vec2](https://hf.rst.im/audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim) for arousal, dominance, valence prediction in range [0,1], used in dimensional Speech Emotion Recognition.
+Acieves xx CCC on [MSP-Podcast](https://ecs.utdallas.edu/research/researchlabs/msp-lab/MSP-Podcast.html) test split.
+
+
+
+# Benchmarks
+CCC based on Test1 and Development sets of the Odyssey Competition
+<table style="width:500px">
+  <tr><th colspan=6 align="center" >Multi-Task Setup</th></tr>
+  <tr><th colspan=3 align="center">Test 3</th><th colspan=3 align="center">Development</th></tr>
+  <tr>   <td>Val</td> <td>Dom</td> <td>Aro</td> <td>Val</td> <td>Dom</td> <td>Aro</td> </tr>
+  <tr>  <td> 0</td> <td>0</td> <td>0</td> <td>0</td> <td>0</td> <td>0</td> </tr>
+</table>
+ 
+
+
+# Usage
+```python
+from transformers import AutoModelForAudioClassification
+import librosa, torch
+
+```