π§
Higgs Tts 2 3b Base model by bosonai
β 62.3
π¬Technical Deep Dive
Full Specifications [+]
π Updated daily
Source summary: Based on Hugging Face metadata. Not a recommendation.
π‘οΈ Model Transparency Report
Technical metadata sourced from upstream repositories.
Open Metadata
π Identity & Source
- id
- hf-model--bosonai--higgs-tts-2-3b-base
- slug
- bosonai--higgs-tts-2-3b-base
- source
- huggingface
- author
- bosonai
- license
- Other
- tags
- transformers, safetensors, higgs_audio_v2, text-to-audio, text-to-speech, en, zh, de, ko, arxiv:2505.23009, license:other, endpoints_compatible, region:us
βοΈ Technical Specs
- architecture
- HiggsAudioV2ForConditionalGeneration
- params billions
- 5.77
- context length
- 4,096
- pipeline tag
- text-to-speech
- vram gb
- 5.6
- vram is estimated
- true
- vram formula
- VRAM β (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)
π Engagement & Metrics
- downloads
- 188,096
- stars
- null
- forks
- null
Data indexed from public sources. Updated daily.