From 92f0831a855fd2cff4f92e617988657b2ba1f5a5 Mon Sep 17 00:00:00 2001 From: palonso Date: Fri, 20 Oct 2023 19:40:00 +0200 Subject: [PATCH] Use MAEST as title in the documentation. This makes a cleaner url for the model and is consistent with other models without reference to the training dataset (e.g., OpenL3, CREPE). --- doc/sphinxdoc/models.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/sphinxdoc/models.rst b/doc/sphinxdoc/models.rst index 1b46f7154..4d4780477 100644 --- a/doc/sphinxdoc/models.rst +++ b/doc/sphinxdoc/models.rst @@ -137,8 +137,8 @@ Models: *Note: We provide models operating with a fixed batch size of 64 samples since it was not possible to port the version with dynamic batch size from ONNX to TensorFlow. Additionally, an ONNX version of the model with* `dynamic batch `_ *size is provided.* -Discogs-MAEST -^^^^^^^^^^^^^ +MAEST +^^^^^ Music Audio Efficient Spectrogram Transformer (`MAEST `_) trained to predict music style labels using an in-house dataset annotated with Discogs metadata. We offer versions of MAEST trained with sequence lengths ranging from 5 to 30 seconds (``5s``, ``10s``, ``20s``, and ``30s``), and trained starting from different intial weights: from random initialization (``fs``), from `DeiT `_ pre-trained weights (``dw``), and from `PaSST `_ pre-trained weights (``pw``). Additionally, we offer a version of MAEST trained following a teacher student setup (``ts``).