KeisukeMiyamoto/whisper-cluster-audio download history
KeisukeMiyamoto/whisper-cluster-audio is an automatic speech recognition dataset on the Hugging Face Hub. In the last 30 days it was downloaded 76 times (25 in the last 7 days), and 446 times in total. It ranks #186,937 among datasets by monthly downloads.
Whisper Cluster Audio Dataset description Whisper Cluster Audio is a Japanese audio dataset containing 1,161,120 speech clips, approximately 5,383.42 hours of audio, automatic transcripts, speech intervals, and frame-level discrete acoustic labels. It supports speech re
Models trained on whisper-cluster-audio
2 models list it as training data.
- KeisukeMiyamoto/zipformer-cpt 45 downloads in 30 days
- KeisukeMiyamoto/lambda-audio-v6 – downloads in 30 days
Open KeisukeMiyamoto/whisper-cluster-audio on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.