metadata
license: other
license_name: research-only-non-commercial-data
license_link: >-
https://github.com/interscript/interscript-models/blob/main/cards/urd-g2p-base-1.0.md
language:
- ur
tags:
- g2p
- byt5
- imf
- urdu
- research-only
metrics:
- cer
urd-g2p-base-1.0
Urdu grapheme-to-phoneme, base tier (run-059): byt5-base seq2seq on the full 610K-pair humair025 corpus. IMF v1 fp32 (2.16 GB).
Metrics (full 12,699-row test split, raw char CER, row-mean)
CER 15.65 (urd-g2p-1.0 small tier: 15.78 baseline) — gate PASSED. Normalized CER 10.75.
Artifact parity (WO51 contract)
Single-row greedy decode, the runtime's actual decode mode: 500-row probe recorded in the artifact metadata (the pre-WO51 batched harness numbers were invalid — batched decode without an attention mask measures nothing).
License — RESEARCH-ONLY
The training corpus (humair025/urdu-g2p-dictionary) is
non-commercial (verified from the dataset card,
github.com/humair-m/urdu-g2p LICENSE). These weights are therefore
released for research use only — owner decision 2026-10-18
(recorded in corpora/urd-g2p-dict.yaml license_review). Code:
BSD-3-Clause.