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
Android GPU note: the measured crash instead of a version floor
Browse filesREADME.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.
- README.md +1 -1
- litertlm_manifest.json +1 -1
README.md
CHANGED
|
@@ -188,7 +188,7 @@ Apart from the parts that name the file of 2026-11-17, this card's measurements
|
|
| 188 |
|
| 189 |
## Known runtime issues
|
| 190 |
|
| 191 |
-
**External weights (since 2026-11-09).** In `VibeVoice-ASR-BitNet.litertlm`, the weights sit in TFLiteWeights sections at the end of the file (LiteRT's external weights) instead of inside the model graph. On
|
| 192 |
|
| 193 |
From a conversation preface (the system message, initial messages, tools and extra context a conversation is created with) that has tools and no messages, LiteRT-LM renders this file's chat template with an empty message list, and the template reads `messages[0]` without checking that the list is non-empty, so the render fails with `Failed to apply template: undefined value`. This happens in two places: when the preface is prefilled at creation (`prefillPrefaceOnInit = true` in Kotlin, `prefillPrefaceOnInit: true` on the web, `SetPrefillPrefaceOnInit(true)` in C++; the default is false), where creating the conversation fails with that error, and in the preface render (`renderPrefaceIntoString()` in Kotlin and Swift, `RenderPrefaceIntoString()` in C++, `litert_lm_conversation_render_preface_to_string` in the C API). The same happens with extra context (such as `enable_thinking`) and no messages, and in the preface render with an empty preface (run in the runtime on one Qwen3 template; the other templates rendered with minijinja 2.14 and jinja2). Read in the source of LiteRT-LM 0.17.0, 0.18.1 and main; measured with LiteRT-LM 0.18.1 (the litert-lm package from PyPI) through its C API on this file's template text. The default path, where the first message is rendered together with the preface, is not affected: the Python API and the CLI of 0.18.1 expose neither the flag nor the preface render, and Google AI Edge Gallery sets neither (its source as read on 2026-10-25). A system message or any initial message in the conversation config avoids it.
|
| 194 |
|
|
|
|
| 188 |
|
| 189 |
## Known runtime issues
|
| 190 |
|
| 191 |
+
**External weights (since 2026-11-09).** In `VibeVoice-ASR-BitNet.litertlm`, the weights sit in TFLiteWeights sections at the end of the file (LiteRT's external weights) instead of inside the model graph. On a Pixel 8a, the GPU engine of the v0.18.0 and v0.18.1 Android builds crashes (SIGSEGV) on a Qwen3-0.6B file with external weights ([LiteRT-LM#3986](https://github.com/google-ai-edge/LiteRT-LM/issues/3986)). The earlier file with the weights inside the graph stays at revision [`193b2d5`](https://huggingface.co/litert-community/VibeVoice-ASR-BitNet/tree/193b2d579a786206286ac36e74b6ea513562bdf5).
|
| 192 |
|
| 193 |
From a conversation preface (the system message, initial messages, tools and extra context a conversation is created with) that has tools and no messages, LiteRT-LM renders this file's chat template with an empty message list, and the template reads `messages[0]` without checking that the list is non-empty, so the render fails with `Failed to apply template: undefined value`. This happens in two places: when the preface is prefilled at creation (`prefillPrefaceOnInit = true` in Kotlin, `prefillPrefaceOnInit: true` on the web, `SetPrefillPrefaceOnInit(true)` in C++; the default is false), where creating the conversation fails with that error, and in the preface render (`renderPrefaceIntoString()` in Kotlin and Swift, `RenderPrefaceIntoString()` in C++, `litert_lm_conversation_render_preface_to_string` in the C API). The same happens with extra context (such as `enable_thinking`) and no messages, and in the preface render with an empty preface (run in the runtime on one Qwen3 template; the other templates rendered with minijinja 2.14 and jinja2). Read in the source of LiteRT-LM 0.17.0, 0.18.1 and main; measured with LiteRT-LM 0.18.1 (the litert-lm package from PyPI) through its C API on this file's template text. The default path, where the first message is rendered together with the preface, is not affected: the Python API and the CLI of 0.18.1 expose neither the flag nor the preface render, and Google AI Edge Gallery sets neither (its source as read on 2026-10-25). A system message or any initial message in the conversation config avoids it.
|
| 194 |
|
litertlm_manifest.json
CHANGED
|
@@ -219,7 +219,7 @@
|
|
| 219 |
}
|
| 220 |
],
|
| 221 |
"known_issues": [
|
| 222 |
-
"
|
| 223 |
"Audio encoder does not run on the GPU delegates: on Metal/WebGPU the 30 s window dispatches 90001+ workgroups per stem kernel (limit 65535); on Adreno (OpenCL, all 1857 nodes delegated) the fp16 path returns an empty transcript; keep audio_backend=cpu",
|
| 224 |
"Audio placeholder tokens <|object_ref_start|>/<|object_ref_end|>/<|box_start|> are added to the tokenizer.json inside the file (ids 151646/151647/151648, the ids the model was trained with); the upstream tokenizer.json has no string for them"
|
| 225 |
],
|
|
|
|
| 219 |
}
|
| 220 |
],
|
| 221 |
"known_issues": [
|
| 222 |
+
"Since 2026-11-09 this file's weights sit in TFLiteWeights sections at the end of the file (LiteRT's external weights). On a Pixel 8a, the GPU engine of the v0.18.0 and v0.18.1 Android builds crashes (SIGSEGV) on a Qwen3-0.6B file with external weights (https://github.com/google-ai-edge/LiteRT-LM/issues/3986). The earlier file with the weights inside the graph stays at revision 193b2d579a786206286ac36e74b6ea513562bdf5 (https://huggingface.co/litert-community/VibeVoice-ASR-BitNet/tree/193b2d579a786206286ac36e74b6ea513562bdf5).",
|
| 223 |
"Audio encoder does not run on the GPU delegates: on Metal/WebGPU the 30 s window dispatches 90001+ workgroups per stem kernel (limit 65535); on Adreno (OpenCL, all 1857 nodes delegated) the fp16 path returns an empty transcript; keep audio_backend=cpu",
|
| 224 |
"Audio placeholder tokens <|object_ref_start|>/<|object_ref_end|>/<|box_start|> are added to the tokenizer.json inside the file (ids 151646/151647/151648, the ids the model was trained with); the upstream tokenizer.json has no string for them"
|
| 225 |
],
|