premove-ai/premove-itn

Premove ITN v0.2.0

This release updates the contextual candidate scorer used by premove-itn. The deterministic Rust candidate generators and exact decoder are unchanged.

Load it through the matching Python package:

from premove_itn import PremoveITN

itn = PremoveITN.from_pretrained(revision="v0.2.0")
print(itn.normalize("meet me at two thirty"))
# meet me at 02:30

Training

The v0.1.0 scorer was adapted for three epochs on 7,440 controlled, single-collision TIME-versus-identifier records. No replay or dual-collision examples were used. Epoch 3 was selected using a separate 200-row development set before any frozen test was inspected.

Results

Metric	v0.1.0	v0.2.0
Context record	51.2%	86.2%
Counterfactual pair	6.4%	72.4%
Identifier	29.6%	98.0%
Time	72.8%	74.4%
Dual span	45.0%	96.0%
Dual sentence exact	16.0%	92.0%
Broad strict exact	40.5%	43.7%

The contextual and dual benchmarks are synthetic controlled evaluations. They do not estimate production voice-agent accuracy. The broad benchmark gained 86 new exact rows and lost 38 previously exact rows. Localized losses were most visible in ORDINAL, MONEY, URL, and DIGIT_SEQUENCE.

Limitations

• TIME recall on the controlled single-collision test is 74.4%, substantially below the 98.0% identifier result.
• The model is English-only and requires the premove-itn candidate graph and decoder. It is not a generic Transformers model.
• The approximately 435.6M-parameter scorer has a large download and multi-second initialization cost.

Release identity

• Artifact version: v0.2.0
• Required package version: 0.2.0
• Hub repository: premove-ai/premove-itn
• Base model: microsoft/deberta-v3-large
• Base revision: 64a8c8eab3e352a784c658aef62be1662607476f
• Source checkpoint SHA-256: 10a338d57b6d619f52259a58aca210ecb78f47de44baf0c25477a8f5b06b5d39
• Model SHA-256: 0b6f36aa32311d0c495e1c5307d5e34463e52b4dc283ab9030bc2f54e1bf1152

Source and evaluation evidence are available from premove-ai/premove-itn.