BranchShine: Compact Raw-Audio-to-IPA Transcription with a RoPE E-Branchformer Encoder
Provides a compact and competitive model for IPA transcription, useful for pronunciation-focused tasks, though incremental over existing methods.
BranchShine, a 33M-parameter raw-audio CTC recognizer, achieves 9.19% IPA character error rate on a multilingual test set, outperforming the 575M-parameter PhoneticXEUS baseline (9.78%) while being much smaller.
Speech-to-IPA transcription is useful when the desired output is pronunciation rather than orthographic text, but competitive multilingual systems are often large and evaluation is sensitive to normalization choices. This paper presents BranchShine, a 33M-parameter raw-audio CTC recognizer with a lightweight convolutional front end and a 19-block RoPE E-Branchformer encoder. We find that BranchShine provides a compact and competitive operating point for IPA transcription under matched normalization and scoring. On a 16,660-utterance multilingual test set covering 41 language labels, BranchShine obtains 9.19% whitespace-insensitive IPA character error rate, compared with 9.78% for the 575.00M-parameter PhoneticXEUS baseline. A secondary child speech reading analysis shows a complementary operating profile: BranchShine is more conservative on incorrect readings, while Whisper-Medium is stronger on exact acceptance of correct readings. Overall, the results indicate that a compact raw-audio-to-IPA model can approach much larger baselines on character-level IPA transcription.