Dynamic Context / Hot words Support for this model just like nvidia/parakeet-tdt-0.6b-v3
#4
by vedapani1 - opened
Based on the Source files, blogs and resources i looked into, nvidia/multitalker-parakeet-streaming-0.6b-v1 deos not support dynamic context/ hot words for better transcriptions. Is that True? if not, can anyone tell me how to pass on the context words / hot words for better trasncriptions.
If this is not supported, it would be great to add this feature in this model, which will make it the ultimate model for ASR with Speaker diarization even for overlapping audio.