Add models

README.md

@@ -1,3 +1,16 @@
 ---
 license: mit
 ---
+
+
+# Note
+
+The provided checkpoints are adapated from the official WavLM models released at https://github.com/microsoft/unilm/blob/master/wavlm/README.md#pre-trained-models to be used for fine-tuning in fairseq.
+
+They should be used together with the specialized fairseq repository https://github.com/Emrys365/fairseq/tree/wavlm where the support for WavLM is added.
+
+> NOTE: The adapted checkpoints are only guaranteed to have the same `model configuration` and `model parameters` as the official released models. The other parameters (such as `task hyperparameters` and `optimizer hyperparameters`) are just a template.
+>
+> Therefore, these adapted checkpoints are only suitable to be used as an initialization for fine-tuning in the downstream tasks, **NOT** for continuing pre-training.
+
+Please refer to https://github.com/Emrys365/fairseq/blob/wavlm/examples/wavlm/README.md#load-adapted-checkpoints-for-fairseq-finetuning for more information.

WavLM-Base+_cpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2305c553c301822c4c06522d1e5e7f2575645a08f2b2e8f9a8ef80cf2d96f3a2
+size 1135291829

WavLM-Base_cpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154aa69ff4ec5399f5e2dfce95fc630d81d809d9b5ec322d5cb7f36d68461035
+size 1135291565

wavlm_large_cpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a12c5cc5e7d61f7f29961e7810b89aa6352894cb7aafd9ed922b10d86f9b3a
+size 2019658005