models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
higgs-audio-v3-tts-4b-transformersMESIE-MultiAudio-v1Discussion-Phi-4-multimodal-instruct-audio-dimp-reasoningDasheng-AudioGen-Multilingualtiny-audio-next-multiasrMESIE-MultiAudio-v1-alphaDiscussion-Phi-4-multimodal-instruct-audioast-audio-analysis-multilabel-modelmultimodal-popularity-classifier-video-text-audio-peft-robustDiscussion-Phi-4-multimodal-instruct-audio-levelDiscussion-Phi-4-multimodal-instruct-audio-dimp-tagaudiotokenizer_emilia_multilang-wav-qwen2.5-3b_saltDiscussion-Phi-4-multimodal-instruct-audio-dimp-tag-beta2Discussion-Phi-4-multimodal-instruct-audio-dimp-onlyDiscussion-Phi-4-multimodal-instruct-audio-dimpDiscussion-Phi-4-multimodal-instruct-audio-level-testDiscussion-Phi-4-multimodal-instruct-audio-dimp-alphadistilhubert_multilabel_audioset_subset_50epochsuniversa-wavlm_base_urgent24_multi-metric_audiorefmultimodal-popularity-classifier-video-text-audio-peftmultimodal-popularity-classifier-video-text-audio-frozenaudio-tokenizer-mel-160.120.80.40-commit-200-recon-400-distill-200-multi-8sec-240kmultilabel-audiomentations-wav2vec2-large-xls-r-300m-dm32Pair_07_08_Multi_audioaudio-tokenizer-mel-40.30.20.10-commit-200-recon-400-distill-100-multi-16sec-5kast-finetuned-audioset-10-10-0.4593-finetuned-multi-label_Processesaudiotokenizer_emilia_multilang-wav-qwen2.5-0.5b_saltCMA-Multimodal-valence-new-audio-regressorMulti-Scale_Hierarchical_Audio_BiLSTMAudio-Voice-Multi-Class-Classifications