speaker diarization less 1s seems not good
1
#6 opened about 3 hours ago
by
linlinsong
seems that the model could not support overlapped speech recognition?
#5 opened about 6 hours ago
by
scutrandom
How many languages are supported?
#4 opened about 7 hours ago
by
RoadToNowhere
Use this model with ROCm and docker
#3 opened about 9 hours ago
by
cool9203
will this model be supported by vllm or sglang?
#2 opened about 16 hours ago
by
feizhai123
Can this model be run on a Turing GPU (No Flash Attention support)?
1
#1 opened about 19 hours ago
by
rsbdev