Upload ears_wham.ckpt

For 48 kHz models [3], we offer pretrained checkpoints for speech enhancement, trained on the EARS-WHAM dataset, and for dereverberation, trained on the EARS-Reverb dataset.

SGMSE+ trained on EARS-WHAM: gdown 1t_DLLk8iPH6nj8M5wGeOP3jFPaz3i7K5
SGMSE+ trained on EARS-Reverb: gdown 1PunXuLbuyGkknQCn_y-RCV2dTZBhyE3V

pretrained_checkpoints/48_khz_models/ears_wham.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2768097c11e8192ce499416c48e67d5085d31cefb63ff928e383dd32817ba2c9
+size 1295841456