README
VibeVoice-ASR-BitNet
Multilingual automatic speech recognition running entirely on CPU with
microsoft/VibeVoice-ASR-BitNet:
an I8_S quantized acoustic/semantic VAE speech tokenizer feeding a ternary
(I2_S, ~1.58 bit) BitNet Qwen2.5-1.5B decoder β 1.58 GB of weights in total.
The model has no PyTorch/CUDA implementation; the only inference path is the
authors' ggml-based VibeASR.cpp
engine, so this Space clones and compiles asr_infer from source on startup and
drives it as a subprocess. It runs entirely on CPU β CPU efficiency is the whole
point of the paper.
Languages: English, Chinese, French, Italian, Korean, Portuguese, Vietnamese.
Example clips come from LibriSpeech (English) and FLEURS (French, Mandarin).
Contributors
10 commits
Similar repos
README
VibeVoice-ASR-BitNet
Multilingual automatic speech recognition running entirely on CPU with
microsoft/VibeVoice-ASR-BitNet:
an I8_S quantized acoustic/semantic VAE speech tokenizer feeding a ternary
(I2_S, ~1.58 bit) BitNet Qwen2.5-1.5B decoder β 1.58 GB of weights in total.
The model has no PyTorch/CUDA implementation; the only inference path is the
authors' ggml-based VibeASR.cpp
engine, so this Space clones and compiles asr_infer from source on startup and
drives it as a subprocess. It runs entirely on CPU β CPU efficiency is the whole
point of the paper.
Languages: English, Chinese, French, Italian, Korean, Portuguese, Vietnamese.
Example clips come from LibriSpeech (English) and FLEURS (French, Mandarin).
Similar repos
Linked in READMEs
Contributors
10 commits