Post
2293
Audio transcription is one of the most useful use cases for journalists (and many other professions!).
@sergeipetrov
,
@reach-vb
,
@pcuenq
, and
@philschmid
have created an optimized Whisper with Speaker Diarization for
@huggingface
Inference Endpoints—definitely worth a read!
Check out their blog post here: https://huggingface.co/blog/asr-diarization
You can find the notebook here: sergeipetrov/asrdiarization-handler
Check out their blog post here: https://huggingface.co/blog/asr-diarization
You can find the notebook here: sergeipetrov/asrdiarization-handler