microsoft
/

VibeVoice-ASR

Automatic Speech Recognition

Model card Files Files and versions

Resources

View closed (1)

Training loss is too high

#17 opened 7 days ago by

how to add customized hotwords ?

#16 opened 7 days ago by

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

#15 opened 9 days ago by

HF Inference Endpoint - for openAI compatible audio streaming

#14 opened 10 days ago by

Is there any parameter to tune for more accurate diarization

#13 opened 15 days ago by

glitch control

#12 opened 15 days ago by

MLX support

#10 opened 18 days ago by

Smaller version?

#9 opened 18 days ago by

its not working on google colab even in my own pc

#8 opened 20 days ago by

Fix typos and formatting

#7 opened 21 days ago by

speaker diarization less 1s seems not good

#6 opened 21 days ago by

seems that the model could not support overlapped speech recognition?

#5 opened 21 days ago by

How many languages are supported?

#4 opened 21 days ago by

Use this model with ROCm and docker

#3 opened 21 days ago by

will this model be supported by vllm or sglang?

#2 opened 21 days ago by

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

#1 opened 22 days ago by