Instructions to use litert-community/VibeVoice-ASR-Streaming-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use litert-community/VibeVoice-ASR-Streaming-1.5B 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-Streaming-1.5B \
  --prompt="Write me a poem"

LiteRT

How to use litert-community/VibeVoice-ASR-Streaming-1.5B 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-Streaming-1.5B 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-Streaming-1.5B")
model = VibeVoiceForConditionalGenerationInference.from_pretrained(
    "litert-community/VibeVoice-ASR-Streaming-1.5B", 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

mlboydaisuke commited on Sep 17

Commit

ce75d5d

verified ·

1 Parent(s): 29df26a

VibeVoice-ASR-Streaming-1.5B: int4-b128 LM + int8 audio encoder (3.47 s window), streaming multi-turn protocol

Browse files

Files changed (2) hide show

.gitattributes +1 -0
VibeVoice-ASR-Streaming-1.5B.litertlm +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ 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
+VibeVoice-ASR-Streaming-1.5B.litertlm filter=lfs diff=lfs merge=lfs -text

VibeVoice-ASR-Streaming-1.5B.litertlm ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3cecb6c4d55feccf129b99d541be0879abf0b194a779979c1d194900881603
+size 1992209664