Skip to content

release: heb-diac-1.1 #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ronaldtse merged 1 commit into from
Aug 25, 2026
Merged

release: heb-diac-1.1 #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 19 additions & 0 deletions models.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,3 +149,22 @@ models:
- {name: sb_homograph_ezafe_norm, value: 77.34, source: interscript/interscript-ml docs/RESULTS.md#fas-g2p-1.0}
parity: {samples: 1000, cer_delta: 0.0}
license: BSD-3-Clause
heb-diac-1.1:
task: diacritization
scripts: [Hebr, Hebr]
precision: fp32
filename: heb.zip
parts:
- url: https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.1/heb.zip.part-00
sha256: 8dac0d62e9b0ac4b137412eaf3a542953f11575f12f66f76cb93d3f5d788fc1b
size: 1500000000
- url: https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.1/heb.zip.part-01
sha256: 230c5ab731ea5f001f802d60b9e9a328c10b43bc311a19ef1974f114384313ed
size: 1280987905
sha256: f0022dde8d06e46e8f08cf0b2f7bbb887a05ed686b90f1d5aa82ca3ef690a0b0
size: 2780987905
metrics:
- {name: der_greedy, value: 16.44, source: rababa/docs/RESULTS.md#hebrew-diacritization}
- {name: der_beam4, value: 16.43, source: rababa/docs/RESULTS.md#hebrew-diacritization}
parity: {samples: 500, cer_delta: 0.0}
license: BSD-3-Clause
37 changes: 20 additions & 17 deletions models/heb-diac/heb-diac-1.1.metadata.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,21 +8,24 @@ opset: 14
decoder: kv
precision: fp32
license: BSD-3-Clause
trained_from: >-
rababa train_hebrew_s46.py — phonikud curriculum (1.5M knesset
weak-pretrain + 73.8K hewiki garnish, then gold FT); checkpoint
rababa-checkpoints:/rababa_hebrew/run-s46-phonikud-plus/run-002-gold-ft/best
trained_from: rababa train_hebrew_s46.py — phonikud curriculum (1.5M knesset weak-pretrain
+ 73.8K hewiki garnish, then gold FT); checkpoint rababa-checkpoints:/rababa_hebrew/run-s46-phonikud-plus/run-002-gold-ft/best
metrics:
- name: der_greedy
value: 16.44
protocol: >-
greedy decode (the v1 runtime path); Nakdimon test split,
5,095 examples; ByT5-base s46
source: rababa/docs/RESULTS.md#hebrew-diacritization
- name: der_beam4
value: 16.43
protocol: >-
beam=4 standard decode (reference quality); Nakdimon test
split, 5,095 examples; ByT5-base s46. Greedy ≈ beam-4 for this
model — the runtime path loses nothing.
source: rababa/docs/RESULTS.md#hebrew-diacritization
- name: der_greedy
value: 16.44
protocol: greedy decode (the v1 runtime path); Nakdimon test split, 5,095 examples;
ByT5-base s46
source: rababa/docs/RESULTS.md#hebrew-diacritization
- name: der_beam4
value: 16.43
protocol: beam=4 standard decode (reference quality); Nakdimon test split, 5,095
examples; ByT5-base s46. Greedy ≈ beam-4 for this model — the runtime path loses
nothing.
source: rababa/docs/RESULTS.md#hebrew-diacritization
parity:
samples: 500
cer_delta: 0.0
sha256:
decoder-kv.onnx: f5c6d56fe4fcc7ad99a8fa9b0936f5554c9a8dd11c612e5a0eb9119b4c5d58bc
decoder.onnx: 6665ab15d65808d0ebd9ae569713457737cebb4c6ca39cc4953ecc7231f3b1c8
encoder.onnx: 09c3d1533a06e98efdf36b3dd3c23c68f0fc80f296431ffcbec919438e409708
Loading