Add visual_student_2m sealed confirm checkpoint

README.md

@@ -0,0 +1,31 @@
+---
+language:
+- en
+tags:
+- audio-visual
+- speech-recognition
+- mcorec
+- chime-9
+- avsr
+library_name: pytorch
+pipeline_tag: automatic-speech-recognition
+---
+
+# MCoRec Visual Student (2.07M)
+
+Checkpoint from the MCoRec / CHiME-9 Task 1 AVSR project closeout.
+
+## Evaluation
+
+- **Split:** official confirmation set (20 sessions / 110 speakers)
+- **Protocol:** distilled visual student
+- **Confirm WER:** `0.6424`
+
+## Files
+
+Weights are uploaded as released training artifacts (`.ckpt` / `.nemo` / `.pt`).
+Use the corresponding project inference stack to load them.
+
+## Collection
+
+Part of [`jtygarfield/avsr-project`](https://huggingface.co/collections/jtygarfield/avsr-project).

s2_student_swap.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93bf676e1e86efcede363c65d0d442604b6217bba6c9895565ec96d8c3d2db2
+size 11973738712