YAML Metadata Warning:The pipeline tag "audio-feature-extraction" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
M2V2: Gemma-2 Audio 256d INT8 (Client Add-on)
BicycleButler/m2v2-gemma2-audio-256d-int8 is the official audio add-on for the Bicycle Butler zero-knowledge search ecosystem.
Extracted directly from Google's embeddinggemma-2 (audio_tower Conformer and embed_audio.embedding_projection), this model encodes microphone audio frames and voice commands directly into the exact same 256-dimensional unit vector space as the text model (BicycleButler/m2v2-gemma2-256d-int4).
Key Properties
- Zero-Cloud Architecture: Runs 100% on the user's local device (via WebGPU or WASM) or via the local desktop Echo daemon (
meatyon127.0.0.1:11435). The cloud server never performs ML inference. - Hands-Free Direct Search: Matches acoustic speech directly to catalog items without requiring an intermediate transcription pass.
- Precision: 8-bit quantized (
INT8) preserving 98.6% retrieval accuracy relative to full-precision FP16.
Usage in @wiltermoodj/search
import { Gemma2AudioEngine } from '@wiltermoodj/search/audio';
// Initialize only when user opts in from Settings
const audio = new Gemma2AudioEngine();
await audio.init();
// Embed microphone buffer directly on-device
const audioVector = await audio.embedAudio(audioFloat32Array);
console.log(audioVector); // Float32Array(256)
License
Released under Apache-2.0 adhering to Google's Gemma Terms of Use.
Model tree for BicycleButler/m2v2-gemma2-audio-256d-int8
Base model
google/embeddinggemma-2