---
title: voxcmp_coreml
canonical_url: "https://www.modelscope.cn/models/aaacccc9990/voxcmp_coreml"
md_url: "https://www.modelscope.cn/models/aaacccc9990/voxcmp_coreml.md"
repository: aaacccc9990/voxcmp_coreml
last_updated: 2026-06-29
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
base_model:
  - openbmb/VoxCPM2
base_model_relation: finetune
library_name:
  - other
frameworks:
  - other
downloads: 10
stars: 0
tags:
  - CoreML
  - ANE
  - AppleNeuralEngine
  - NeuralEngine
  - TTS
---

# voxcmp_coreml

> voxcmp_coreml - aaacccc9990 在 ModelScope 开源的模型。voxcmp2 ane

aaacccc9990/voxcmp_coreml 是 ModelScope 魔搭社区上的text-to-speech模型，基于 openbmb/VoxCPM2 构建。

- **Repository**: aaacccc9990/voxcmp_coreml
- **Tasks**: text-to-speech
- **Base model**: openbmb/VoxCPM2
- **Tags**: CoreML, ANE, AppleNeuralEngine, NeuralEngine, TTS
- **Downloads**: 10
- **Stars**: 0
- **Last updated**: 2026-06-29

Source: https://www.modelscope.cn/models/aaacccc9990/voxcmp_coreml

---

# VoxCPM2 ANE

This repository contains the Apple Neural Engine (ANE) optimized CoreML export of the [openbmb/VoxCPM2](https://huggingface.co/openbmb/VoxCPM2) Text-to-Speech (TTS) model.

These models have been converted to Apple's `.mlmodelc` / `.mlpackage` format to leverage hardware acceleration provided by the Apple Neural Engine on Apple Silicon devices. This enables highly efficient and fast on-device text-to-speech generation.

## Model Components

The overall `voxcpm2` TTS pipeline is broken down into several CoreML sub-modules:

- **Language Models (LM)**: `base_lm_multifunction.mlmodelc`, `residual_lm_fused_multifunction.mlmodelc`
- **Audio VAE**: `audio_vae_encoder.mlmodelc`, `audio_vae_decoder_lf4.mlmodelc`
- **Feature Encoder**: `feat_encoder.mlmodelc`
- **Diffusion Transformer (DiT)**: `locdit_p4_c4.mlmodelc`
- **Quantization & Projections**: `fsq_s4.mlmodelc`, `projections.mlmodelc`

## Architecture Highlights
Based on the `config.json`, the model utilizes:
- A base Language Model with 28 layers and 2048 hidden size.
- A Residual LM with 8 layers.
- An Audio VAE supporting up to 48kHz output sample rate.
- A DiT component with 12 layers and 1024 hidden dimension for precise audio modeling.