Modelpublic

bosonai/higgs-audio-v3-8b-stt

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

16likes85downloads

diropen_asr_leaderboard/

file.gitattributes2 KBdownload

fileadded_tokens.json1 KBdownload

fileattention.py9 KBdownload

filecommon.py1 KBdownload

fileconfig.json6 KBdownload

fileconfiguration_higgs_audio.py10 KBdownload

filecuda_graph_runner.py5 KBdownload

filecustom_modules.py6 KBdownload

filegeneration_config.json147 Bdownload

filehiggs_audio_collator.py36 KBdownload

filemerges.txt1.6 MBdownload

filemodel-00001-of-00004.safetensors4.57 GBdownload

filemodel-00002-of-00004.safetensors4.58 GBdownload

filemodel-00003-of-00004.safetensors4.64 GBdownload

filemodel-00004-of-00004.safetensors2.80 GBdownload

filemodel.safetensors.index.json71 KBdownload

filemodeling_higgs_audio_xcodec.py20 KBdownload

filemodeling_higgs_audio.py108 KBdownload

fileREADME.md4 KBdownload

filespecial_tokens_map.json616 Bdownload

filetokenizer_config.json12 KBdownload

filetokenizer.json10.9 MBdownload

filetranscribe.py14 KBdownload

fileutils.py36 KBdownload

filevocab.json2.6 MBdownload

bosonai/higgs-audio-v3-8b-stt · main · files are served by the source, never re-hosted here