Resources

Hosted API for VibeVoice-ASR

#27 opened about 18 hours ago by

Neil233

Speaker diarization - which layers are responsible?

#26 opened 4 months ago by

deathknight0

GGUF + pure-C++ runtime in CrispASR — VibeVoice-ASR (7B) on a 16 GB box

#25 opened 4 months ago by

cstr

Real-world data point: VibeVoice-ASR on Twitter/X Spaces audio (crypto-AI vocabulary)

#24 opened 4 months ago by

AOK-Web3

Built a local macOS menubar dictation app on top of VibeVoice-ASR

👍 1

#23 opened 4 months ago by

Sohaib503

Very unstable inference

👍 3

#22 opened 5 months ago by

andypotato

32GiB VRAM inference using Docker- my working setup

#21 opened 6 months ago by

BigBlueWhale

VibeVoice ASR is part of Transformers from v5.3.0

🔥 2

#20 opened 6 months ago by

bezzam

Fix typo (spelling mistake) on model card

#19 opened 6 months ago by

MihaiPopa-1

Training loss is too high

#17 opened 7 months ago by

mrigankr

how to add customized hotwords ?

#16 opened 7 months ago by

wganson

The checkpoint you are trying to load has model type `vibevoice` but Transformers does not recognize this architecture

#15 opened 7 months ago by

Brunofls8

HF Inference Endpoint - for openAI compatible audio streaming

#14 opened 7 months ago by

sandorkonya

Is there any parameter to tune for more accurate diarization

👍 5

#13 opened 7 months ago by

lingxue156

glitch control

#12 opened 7 months ago by

HEISOV

MLX support

👍 3

#10 opened 7 months ago by

evewashere

Smaller version?

👍 1

#9 opened 7 months ago by

evewashere

its not working on google colab even in my own pc

#8 opened 7 months ago by

malekchouaya

Fix typos and formatting

👍🤯 2

#7 opened 7 months ago by

urroxyz

speaker diarization less 1s seems not good

#6 opened 7 months ago by

linlinsong

seems that the model could not support overlapped speech recognition?

👍 3

#5 opened 7 months ago by

scutrandom

How many languages are supported?

#4 opened 7 months ago by

RoadToNowhere

Use this model with ROCm and docker

#3 opened 7 months ago by

cool9203

will this model be supported by vllm or sglang?

#2 opened 7 months ago by

feizhai123

Can this model be run on a Turing GPU (No Flash Attention support)?

#1 opened 7 months ago by

rsbdev