Frieve-A commited on
Commit
00940a9
路
verified 路
1 Parent(s): af56961

Fix model-card license links

Browse files

Point both license links to the LICENSE file viewer and refresh the README size and SHA-256 in release-manifest.json.

Files changed (2) hide show
  1. README.md +2 -2
  2. release-manifest.json +2 -2
README.md CHANGED
@@ -15,7 +15,7 @@ tags:
15
  Trained weights for the paper [JIT-MPE: Just-in-Time Multi-Pitch Estimation under Output Deadlines](https://arxiv.org/abs/2610.33113)
16
  (Yoshiyuki Kobayashi, Frieve, 2026).
17
  [Source code](https://github.com/Frieve-A/jit-mpe/tree/08bbd5acbb223962895f847a86c2d47a36179896) 路
18
- [Paper page](https://huggingface.co/papers/2610.33113) 路 [License](LICENSE) 路 [Data and software credits](THIRD_PARTY.md)
19
 
20
  JIT-MPE is a small causal model (about 86k parameters) that estimates which of the 88 piano pitches are sounding in
21
  mixed-ensemble audio. It processes the audio in 20 ms frames and can revise a frame until its output deadline
@@ -177,7 +177,7 @@ deadlines. The models do not identify instruments and do not produce note events
177
 
178
  ## License and citation
179
 
180
- The code and these weights are released by the author under the [MIT license](LICENSE). This does not cover the
181
  training datasets or external models, which keep their own licenses. In particular, the Schubert Winterreise
182
  recordings have their own conditions, described in the original dataset release.
183
 
 
15
  Trained weights for the paper [JIT-MPE: Just-in-Time Multi-Pitch Estimation under Output Deadlines](https://arxiv.org/abs/2610.33113)
16
  (Yoshiyuki Kobayashi, Frieve, 2026).
17
  [Source code](https://github.com/Frieve-A/jit-mpe/tree/08bbd5acbb223962895f847a86c2d47a36179896) 路
18
+ [Paper page](https://huggingface.co/papers/2610.33113) 路 [License](https://huggingface.co/Frieve-A/jit-mpe/blob/main/LICENSE) 路 [Data and software credits](THIRD_PARTY.md)
19
 
20
  JIT-MPE is a small causal model (about 86k parameters) that estimates which of the 88 piano pitches are sounding in
21
  mixed-ensemble audio. It processes the audio in 20 ms frames and can revise a frame until its output deadline
 
177
 
178
  ## License and citation
179
 
180
+ The code and these weights are released by the author under the [MIT license](https://huggingface.co/Frieve-A/jit-mpe/blob/main/LICENSE). This does not cover the
181
  training datasets or external models, which keep their own licenses. In particular, the Schubert Winterreise
182
  recordings have their own conditions, described in the original dataset release.
183
 
release-manifest.json CHANGED
@@ -9,8 +9,8 @@
9
  "size": 1087
10
  },
11
  "README.md": {
12
- "sha256": "7739fd3adba5a0bbfa4567b03ef8849db841605b3fe1594a7c808642ed464410",
13
- "size": 9159
14
  },
15
  "THIRD_PARTY.md": {
16
  "sha256": "bb0b57a698d572aad6483dede2665646da8d6aa98759af10f97517ea7b02a87a",
 
9
  "size": 1087
10
  },
11
  "README.md": {
12
+ "sha256": "412f4b60a701fe16b026cfcea0e21f1f59679f5c51ac1aa3762e75520a5f9a99",
13
+ "size": 9259
14
  },
15
  "THIRD_PARTY.md": {
16
  "sha256": "bb0b57a698d572aad6483dede2665646da8d6aa98759af10f97517ea7b02a87a",