Apriel Voice 27B, 음성·추론·도구 활용을 통합한 오픈 모델
Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use
- 매체
- Hugging Face
- 게시
- 중요도
- 3/5
- 화제 지수
- 13
한국어 요약
음성 입력 처리, 추론, 도구 호출을 하나의 백본에서 수행하는 27억 파라미터 규모의 음성-언어 모델 Apriel Voice 27B Preview를 공개했다. Gemma 4 26B-A4B 기반으로 2단계 학습을 거쳐 Big Bench Audio에서 98.90점, Speech-BFCL에서 81.13점을 달성했으며 평균 지연은 1.91초다.
원문 발췌 · English
A capable voice assistant must do more than recognize words; it must understand requests, reason over context, sustain conversations, and act through tools. We present Apriel Voice 27B Preview, an open speech-language model that unifies these capabilities within a shared reasoning backbone while retaining text and image input modalities. Built on the post-trained Gemma 4 26B-A4B checkpoint, Apriel Voice directly processes speech and generates both responses and tool calls without requiring a separate dialogue model. We introduce a two-stage training procedure to adapt the model to speech. The first stage establishes the speech interface, while the second jointly adapts the projector and backbone through supervised fine-tuning, text replay, and source-dependent cross-entropy and forward Kullback--Leibler divergence supervision. Automatically constructed speech-conditioned dialogues provide conversational training data, while local teacher serving, overlapping teacher and student computation, and fused full-vocabulary losses enable efficient online distillation. In thinking mode, Apriel Voice achieves a score of 98.90 on Big Bench Audio, 81.13 on Speech-BFCL, and a task success rate of 65.51% on τ-Voice, with a mean latency of 1.91 seconds. It also achieves 51.27% English EVA accuracy and 74.13% experience pass@1. Finally, we deploy Apriel Voice 27B Preview on a custom serving platform to support interactive voice interactions.