Audio understanding models
Models that classify, recognize, or extract information from audio
Where it stands
Open models163 products0.95× its peers
Fastest products
1scragnog/MOSS-Music-8B-Instruct-GGUF · Open models166×
2Aniemore/wavlm-emotion-russian-resd · Open models38×
3mlboydaisuke/Qwen2.5-Omni-3B-Audio-CoreAI · Open models9.5×
4facebook/mms-lid-512 · Open models7.8×5labhamlet/wavjepa-base · Open models6.2×
6laion/voiceclap-large-v2 · Open models6.0×7yky-h/japanese-hubert-large · Open models5.4×
8slprl/mhubert-base-25hz · Open models4.5×
9TencentGameMate/chinese-hubert-large · Open models4.2×
10m-a-p/MERT-v1-95M · Open models3.6×11aufklarer/Silero-VAD-v5-CoreML · Open models3.4×
12microsoft/wavlm-base-plus-sd · Open models3.3×
13mirek190/audio.cpp · Open models3.1×
14awsaf49/sonics-spectttra-gamma-5s · Open models2.9×
15facebook/sam-audio-large-tv · Open models2.9×16mlx-community/mel-roformer-mlx · Open models2.8×
17speechbrain/spkrec-resnet-voxceleb · Open models2.7×
18speechbrain/vad-crdnn-libriparty · Open models2.7×
19LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF · Open models2.7×20facebook/sam-audio-base-tv · Open models2.6×21MIT/ast-finetuned-audioset-14-14-0.443 · Open models2.6×22onnx-community/wespeaker-voxceleb-resnet34-LM · Open models2.6×
23espnet/hubert_dummy · Open models2.5×
24dima806/english_accents_classification · Open models2.5×
25hf-audio/xcodec-hubert-general · Open models2.5×
207 products carry this theme. “× its peers” is the theme's median growth against the place's median.