SUST-CSE-Speech/banspeech download history
SUST-CSE-Speech/banspeech is an automatic speech recognition dataset on the Hugging Face Hub. In the last 30 days it was downloaded 199 times (23 in the last 7 days), and 4,454 times in total. It ranks #67,876 among datasets by monthly downloads.
Dataset Card for BanSpeech Dataset Summary BanSpeech is a publicly available human-annotated Bangladeshi standard Bangla multi-domain automatic speech recognition (ASR) benchmark. This benchmark contains approximately 6.52 hours of human-annotated broadcast speech, totaling 80
Models trained on banspeech
6 models list it as training data.
- mradermacher/Orpheus-bangla-GGUF 464 downloads in 30 days
- asif00/orpheus-bangla-tts 345 downloads in 30 days
- asif00/orpheus-bangla-tts-gguf 57 downloads in 30 days
- asif00/orpheus-bangla-tts-gguf-8bit 33 downloads in 30 days
- asif00/orpheus-bangla-tts-4bit 15 downloads in 30 days
- noor-raghib-12/orpheus_3b_sft_fp32 10 downloads in 30 days
Open SUST-CSE-Speech/banspeech on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.