Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
SoraWatermarkRemover
Log In
Sign Up
bosonai
/
higgs-audio-v2-generation-3B-base
like
632
Follow
BosonAI
356
Text-to-Speech
Safetensors
4 languages
higgs_audio
arXiv:
2505.23009
License:
other
Model card
Files
Files and versions
xet
Community
22
a30e8ac
higgs-audio-v2-generation-3B-base
11.6 GB
2 contributors
History:
5 commits
xingjian-bosonai
Update README.md
a30e8ac
verified
4 months ago
.gitattributes
2 kB
Upload figures
4 months ago
README.md
9.57 kB
Update README.md
4 months ago
config.json
Safe
6.26 kB
Upload model weights
4 months ago
emergent-tts-emotions-win-rate.png
619 kB
xet
Upload figures
4 months ago
generation_config.json
Safe
147 Bytes
Upload model weights
4 months ago
higgs_audio_tokenizer_architecture.png
Safe
117 kB
xet
Upload figures
4 months ago
higgs_audio_v2_architecture_combined.png
Safe
438 kB
xet
Upload figures
4 months ago
higgs_audio_v2_open_source_delay_pattern.png
Safe
33 kB
Upload figures
4 months ago
model-00001-of-00003.safetensors
Safe
4.97 GB
xet
Upload new weights
4 months ago
model-00002-of-00003.safetensors
Safe
4.98 GB
xet
Upload new weights
4 months ago
model-00003-of-00003.safetensors
Safe
1.59 GB
xet
Upload new weights
4 months ago
model.safetensors.index.json
Safe
31.1 kB
Upload model weights
4 months ago
special_tokens_map.json
Safe
301 Bytes
Upload model weights
4 months ago
tokenizer.json
Safe
17.2 MB
xet
Upload model weights
4 months ago
tokenizer_config.json
Safe
50.3 kB
Upload model weights
4 months ago
