Instructions to use luweigen/vibevoice-asr-streaming-android with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luweigen/vibevoice-asr-streaming-android with LiteRT:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use luweigen/vibevoice-asr-streaming-android with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf luweigen/vibevoice-asr-streaming-android:Q4_0
# Run inference directly in the terminal:
llama cli -hf luweigen/vibevoice-asr-streaming-android:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf luweigen/vibevoice-asr-streaming-android:Q4_0
# Run inference directly in the terminal:
llama cli -hf luweigen/vibevoice-asr-streaming-android:Q4_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf luweigen/vibevoice-asr-streaming-android:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf luweigen/vibevoice-asr-streaming-android:Q4_0

Use Docker

docker model run hf.co/luweigen/vibevoice-asr-streaming-android:Q4_0

Llama new
LM Studio
Jan
Ollama
How to use luweigen/vibevoice-asr-streaming-android with Ollama:
```
ollama run hf.co/luweigen/vibevoice-asr-streaming-android:Q4_0
```
Unsloth Desktop

How to use luweigen/vibevoice-asr-streaming-android with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf luweigen/vibevoice-asr-streaming-android:Q4_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "luweigen/vibevoice-asr-streaming-android:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use luweigen/vibevoice-asr-streaming-android with Docker Model Runner:
```
docker model run hf.co/luweigen/vibevoice-asr-streaming-android:Q4_0
```

Lemonade

How to use luweigen/vibevoice-asr-streaming-android with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull luweigen/vibevoice-asr-streaming-android:Q4_0

Run and chat with the model

lemonade run user.vibevoice-asr-streaming-android-Q4_0

List all available models

lemonade list

Hermes Agent

How to use luweigen/vibevoice-asr-streaming-android with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf luweigen/vibevoice-asr-streaming-android:Q4_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default luweigen/vibevoice-asr-streaming-android:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use luweigen/vibevoice-asr-streaming-android with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf luweigen/vibevoice-asr-streaming-android:Q4_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "luweigen/vibevoice-asr-streaming-android:Q4_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

luweigen commited on 15 days ago

Commit

56d3f21

verified ·

1 Parent(s): ce6ac2e

Upload models for the Android app

Browse files

Files changed (8) hide show

.gitattributes +2 -0
README.md +27 -0
encoder.ns_ctx.onnx +3 -0
encoder.ns_ctx_qnn.bin +3 -0
encoder.static.onnx +3 -0
encoder.static.onnx.data +3 -0
lm-q4_0.gguf +3 -0
special_embeds.bin +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+encoder.static.onnx.data filter=lfs diff=lfs merge=lfs -text
+lm-q4_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,27 @@

+---
+license: mit
+base_model: microsoft/VibeVoice-ASR-Streaming-1.5B
+tags:
+- automatic-speech-recognition
+- streaming
+- onnx
+- gguf
+- android
+- qnn
+---
+# VibeVoice-ASR-Streaming-1.5B — models prepared for Android
+Derived from [microsoft/VibeVoice-ASR-Streaming-1.5B](https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-1.5B) (MIT)
+for the native Android app in the `vibevoice-android` project. Files are downloaded by the app and checked against sha256 values compiled into the APK.
+See the original model card for intended use, limitations and the license.
+| File | What | Runs on |
+|---|---|---|
+| `encoder.ns_ctx.onnx` + `encoder.ns_ctx_qnn.bin` | Speech encoder (acoustic + semantic tokenizer encoders and connectors), audio[1,83200] → feats[1,26,1536], fp16, QNN HTP context binary compiled offline with onnxruntime-qnn 2.7.0 (QNN 2.51). RMSNorm inputs are pre-scaled by powers of two (eps scaled to match) so that fp16 on the HTP does not flush eps to zero | Snapdragon 8 Elite (SM8750, HTP v79) only; device needs qnn-runtime ≥ 2.51 |
+| `encoder.static.onnx` + `encoder.static.onnx.data` | The same encoder, fp32, static shapes, FFN as 1×1 convolutions | Any device, ONNX Runtime CPU EP |
+| `lm-q4_0.gguf` | The Qwen2-1.5B language model as GGUF (Q4_0), Qwen2 BPE tokenizer included. The token embedding table is the model's own; no other changes | llama.cpp (CPU, OpenCL, Hexagon) |
+| `special_embeds.bin` | float32 [2, 1536]: embeddings of the speech start / end tokens that wrap each chunk's audio features | — |
+The acoustic latent uses the mean of the VAE posterior (no sampling), which matches the official sampling mode in WER (docs/models.md of the project).
+Streaming protocol: every 2.93 s of audio (window 3.47 s incl. lookahead), prefill `[speech_start, 26 features, speech_end]`, decode greedily to `<|text_chunk_end|>`, feed it back; the KV cache is kept across chunks.

encoder.ns_ctx.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6844ae5a2e5500c7da94bf9dc0c191ff9c736625f4ba876c946ba3db14758389
+size 707

encoder.ns_ctx_qnn.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:55501692b4db8e4c0607d7c741b65ea29629e6071990de51b84f5ed39ec3e467
+size 1583525888

encoder.static.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4000ef70a29299f4f0b76f8c9f5c3cb7a9f9696a7f54a5701d68a86f53f95990
+size 271231

encoder.static.onnx.data ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:07a057b6af6b0c97148609c5583681633172c44eaefea203a5eab3a16e6f3ef5
+size 2772992000

lm-q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:49936d515d8f02d1a1ca8e2fd39cbdaf2f324fba98d07eeeed23b7493d83efaa
+size 934955680

special_embeds.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c59879339b189df5fbcfb390fdfac6ae2c1381718161dbd43ab1614b537e3b0d
+size 12288