Downloads · 30 days
64
26% of all-time downloads
lam-a2e
adolon-ai/lam-a2e
lam-a2e is a machine learning model from adolon-ai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for onnxruntime. The card lists the license as apache-2.0.
Wav2Vec2-based model fine-tuned for real-time audio-to-expression (A2E) inference. Outputs 52 ARKit blendshape weights at 30fps for avatar lip sync.
All-time downloads
250
Public
Repo size
2.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data402 MB · 100%
At a glance
- Library
- onnxruntime
- License
- apache-2.0
- Model type
- wav2vec2-a2e
- Access
- Public
- Created
- Feb 18, 2026
- Updated
- Jul 26, 2026
- SHA
- 80b0a405
Model card
From the Hugging Face model README
LAM A2E — Lip Animation Model
Wav2Vec2-based model fine-tuned for real-time audio-to-expression (A2E) inference. Outputs 52 ARKit blendshape weights at 30fps for avatar lip sync.
Part of the @omote/core SDK - the first open source client-side AI character SDK for the web.
Variants
Desktop (WebGPU)
| File | Size | Description |
|---|---|---|
model_fp16.onnx | 385 KB | ONNX graph (external data format) |
model_fp16.onnx.data | 192 MB | fp16 weights |
- Backend: WebGPU (preferred) / WASM
- Input: 16kHz audio, fixed 16000 samples
- Output: 52 ARKit blendshapes + CTC ASR (dual-head)
- Precision: Surgical mixed fp16 -- decomposed LayerNorm subgraphs kept in fp32
iOS / Safari (WASM)
| File | Size | Description |
|---|---|---|
lam_ios.onnx | 230 KB | ONNX graph (external data format, opset 18) |
lam_ios.onnx.data | 192 MB | fp16 weights |
- Backend: WASM only
- Input: 16kHz audio, fixed 16000 samples
- Output: 52 ARKit blendshapes (no CTC head)
- Optimizations: 32 fused native LayerNormalization ops, 54.6% node reduction (1339→608)
Quick Start
import { createA2E } from '@omote/core';
// Zero-config — auto-detects platform, uses this HuggingFace CDN
const a2e = createA2E();
await a2e.load();
const { blendshapes } = await a2e.infer(audioSamples);
// blendshapes: Float32Array[52] — ARKit weights at 30fps
ARKit Blendshapes (52)
eyeBlinkLeft, eyeLookDownLeft, eyeLookInLeft, eyeLookOutLeft, eyeLookUpLeft,
eyeSquintLeft, eyeWideLeft, eyeBlinkRight, eyeLookDownRight, eyeLookInRight,
eyeLookOutRight, eyeLookUpRight, eyeSquintRight, eyeWideRight,
jawForward, jawLeft, jawRight, jawOpen,
mouthClose, mouthFunnel, mouthPucker, mouthLeft, mouthRight,
mouthSmileLeft, mouthSmileRight, mouthFrownLeft, mouthFrownRight,
mouthDimpleLeft, mouthDimpleRight, mouthStretchLeft, mouthStretchRight,
mouthRollLower, mouthRollUpper, mouthShrugLower, mouthShrugUpper,
mouthPressLeft, mouthPressRight, mouthLowerDownLeft, mouthLowerDownRight,
mouthUpperUpLeft, mouthUpperUpRight,
browDownLeft, browDownRight, browInnerUp, browOuterUpLeft, browOuterUpRight,
cheekPuff, cheekSquintLeft, cheekSquintRight,
noseSneerLeft, noseSneerRight, tongueOut
License
Apache 2.0
- Library
- onnxruntime
- Type
- wav2vec2-a2e
- License
- apache-2.0
- Created
- Feb 18, 2026
- Updated
- Jul 26, 2026