Automatic Speech Recognition
LiteRT-LM
LiteRT
VibeVoice
litertlm
on-device
edge
asr
speech-recognition
audio
bitnet
Instructions to use litert-community/VibeVoice-ASR-BitNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use litert-community/VibeVoice-ASR-BitNet with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run # (or pass its name right after the repo id). litert-lm run \ --from-huggingface-repo=litert-community/VibeVoice-ASR-BitNet \ --prompt="Write me a poem"
- LiteRT
How to use litert-community/VibeVoice-ASR-BitNet 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
- VibeVoice
How to use litert-community/VibeVoice-ASR-BitNet with VibeVoice:
import torch, soundfile as sf, librosa, numpy as np from vibevoice.processor.vibevoice_processor import VibeVoiceProcessor from vibevoice.modular.modeling_vibevoice_inference import VibeVoiceForConditionalGenerationInference # Load voice sample (should be 24kHz mono) voice, sr = sf.read("path/to/voice_sample.wav") if voice.ndim > 1: voice = voice.mean(axis=1) if sr != 24000: voice = librosa.resample(voice, sr, 24000) processor = VibeVoiceProcessor.from_pretrained("litert-community/VibeVoice-ASR-BitNet") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "litert-community/VibeVoice-ASR-BitNet", torch_dtype=torch.bfloat16 ).to("cuda").eval() model.set_ddpm_inference_steps(5) inputs = processor(text=["Speaker 0: Hello!\nSpeaker 1: Hi there!"], voice_samples=[[voice]], return_tensors="pt") audio = model.generate(**inputs, cfg_scale=1.3, tokenizer=processor.tokenizer).speech_outputs[0] sf.write("output.wav", audio.cpu().numpy().squeeze(), 24000) - Notebooks
- Google Colab
- Kaggle
Commit History
3 days ago
-
Android GPU note: the measured crash instead of a version floor
Verified signatureREADME.md and litertlm_manifest.json: the note on Android GPU builds now says what was measured (on a Pixel 8a, the GPU engine of the v0.18.0 and v0.18.1 Android builds crashes on a Qwen3-0.6B file with external weights) instead of a LiteRT-LM version floor.fcd2700
5 days ago
-
README and manifest notes: plainer wording ("chunked by the runtime"; the 20 LibriSpeech clips named)
Verified signature3835eff -
README: the time of the 2026-11-17 file replacement in UTC (11:58 UTC), the Python example run with the new file, and plainer wording; manifest notes reworded the same way
Verified signaturea37547b -
Prefill/decode graph in the GPU composite form (weights unchanged); card and manifest updated with the 2026-11-17 Galaxy S26 and Pixel 11 Pro runs
Verified signature9e0df43
6 days ago
-
Card: plainer wording
Verified signature- Wording: plain words for the parts of a measurement (runs, configurations, table cells, phone reservations).0d3aca6
13 days ago
-
litertlm_manifest.json: VibeVoice-ASR-BitNet.litertlm's sha256, size and sections after the move to external weights; min runtime 0.19.0 and the Android GPU known issue (LiteRT-LM#3986)
Verified signature6d64def -
VibeVoice-ASR-BitNet.litertlm: weights moved to TFLiteWeights sections at the end of the file (LiteRT external weights); Android GPU needs LiteRT-LM 0.19.0 or later
Verified signatured7805b0
28 days ago
-
Add a known runtime issue: a preface with tools and no messages fails to render the chat template
Verified signatureAdds the lines under Known runtime issues; nothing else in the card changes.193b2d5
-
Say that the CLI's Init counts engine creation twice (LiteRT-LM #4057)
Verified signatureThe CLI's printed Init includes both Init Total and the phases inside it. One sentence, no number changed.338b946
-
manifest 0.1.3: capabilities.thinking.control = never (what the bundle's template does about thinking, derived from the template inside the bundle)
Verified signaturea4099fc
-
Card: the Python usage block now runs on litert-lm-api 0.16.1 / 0.17.1 (send_message returns a dict; response_text() helper)
Verified signature32afe2d
-
Card: measured device / browser results (edge-compat, 2026-09)
Verified signature4c72feb
-
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signaturef119893 -
litertlm_manifest.json (public, derived from the bundle header + curated rows)
Verified signatureadc6245 -
MIT LICENSE (inherited from microsoft/VibeVoice)
Verified signature9ed3b48 -
VibeVoice-ASR-BitNet: int4-b128 ternary LM + int8 audio encoder (30 s window), generic audio path
Verified signaturebf07205 -
VibeVoice-ASR-BitNet LiteRT-LM card
Verified signature56e6a26 -
initial commit
Verified signatureb79b5e8