EmbeddingGemma 2 被改造为端侧语音转写工具，MacBook Air 一小时音频约 13 秒处理完
An hour of audio transcribed in about 13s on MacBook Air
开发者基于 Google EmbeddingGemma 2 多模态嵌入模型构建端侧 STT 工具 Embedding Gemma Transcribe，只额外训练一个小型 reader 把音频片段映射到约 22.9 万词的英文文本空间。
把 EmbeddingGemma 2 的音频向量空间直接解码为英文文本，在 M3 MacBook Air 上跑到约 288 倍实时，展示了非传统 STT 路线的可行性与速度上限。
Google's EmbeddingGemma 2 is an embedding model. We turned it into a speech-to-text model: an hour of audio in about 13 seconds on a base MacBook Air, entirely on device.
Download for Mac (free)
v1.6 · macOS 14+ · Apple Silicon
models download on first launch (715 MB)
Can an embedding model transcribe speech?
EmbeddingGemma 2 is a multimodal embedding model: text, images, audio and video in one shared space. Say a word out loud and its audio lands close to the written word.
So we tried reading words straight out of that space.
How it works
- EmbeddingGemma 2's audio encoder stays exactly as it is.
- A small reader moves each short slice of audio into the model's text space.
- The closest of ~229,000 English words wins, and the slices become a transcript.
- A tiny extra model adds punctuation and capitals.
Only the reader is trained: under two hours on 8×H100, on openly licensed English speech. The base model was never trained for speech-to-text.
How fast?
| Model | Runs on | Mac | Speed |
|---|---|---|---|
| Embedding Gemma Transcribe | Neural Engine | base M3 MacBook Air, 8 GB | 288×1 hour in 12.6 s |
| IBM Granite Speech 5.0 TurboCTC | GPU (MLX) | base M3 MacBook Air, 8 GB | ~150×1 hour in 25.7 s |
| NVIDIA Parakeet TDT 0.6B v3 (FluidAudio) | Neural Engine | M4 Pro | 156× |
| NVIDIA Parakeet TDT 0.6B v3 (FluidAudio) | Neural Engine | M5 Pro | 335× |
| Phonon-2, a Parakeet v3 fine-tune (FluidAudio) | Neural Engine | M5 Pro | 480× |
× real time: seconds of audio per second of processing. Rows 1–2: our tests on the same base M3 MacBook Air. Rows 3–5: FluidAudio's published benchmarks on larger, newer Macs and different audio. A rough guide, not a like-for-like ranking.
Where it stands
Its word error rate is about 5% right now, against 2–3% for leading speech models. We believe a better-trained reader can close that gap; that's the next iteration.
Use it
Drop in an audio file, or hold Right Option, speak and release to dictate into any app. It runs on the Mac's Neural Engine; your audio never leaves the machine.
来源：Hacker News · eg2.haku.sh