Vocabulary Constrained Decoding With Language Model Integration

via “vocabulary-constrained-decoding”

automatic-speech-recognition model by undefined. 48,72,389 downloads.

Unique: Implements vocabulary constraints via masked beam search decoding, restricting token selection at each step to predefined vocabulary. Operates within the standard Whisper decoding pipeline without requiring model retraining or fine-tuning.

vs others: Simpler to implement than domain-specific fine-tuning because it requires only vocabulary lists, not labeled training data; however, less accurate than fine-tuned models because the base model is not adapted to the domain, and constrained decoding forces suboptimal token choices.