Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
stepfun-ai
/
Step-Audio-2-mini
like
240
Follow
StepFun
1.66k
Any-to-Any
Transformers
ONNX
Safetensors
English
Chinese
step_audio_2
text-generation
custom_code
arxiv:
2507.16632
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
14
Deploy
Use this model
49e90d2
Step-Audio-2-mini
17.9 GB
5 contributors
History:
3 commits
petronny
updated readme
49e90d2
verified
4 months ago
assets
updated readme
4 months ago
token2wav
added model files
4 months ago
.gitattributes
1.68 kB
updated readme
4 months ago
README.md
32.3 kB
updated readme
4 months ago
added_tokens.json
173 kB
added model files
4 months ago
config.json
973 Bytes
added model files
4 months ago
configuration_step_audio_2.py
1.81 kB
added model files
4 months ago
merges.txt
1.67 MB
added model files
4 months ago
model-00001-of-00004.safetensors
4.93 GB
xet
added model files
4 months ago
model-00002-of-00004.safetensors
4.93 GB
xet
added model files
4 months ago
model-00003-of-00004.safetensors
4.99 GB
xet
added model files
4 months ago
model-00004-of-00004.safetensors
1.78 GB
xet
added model files
4 months ago
model.safetensors.index.json
64.6 kB
added model files
4 months ago
modeling_step_audio_2.py
16.6 kB
added model files
4 months ago
special_tokens_map.json
819 Bytes
added model files
4 months ago
tokenizer.json
12.7 MB
xet
added model files
4 months ago
tokenizer_config.json
1.2 MB
added model files
4 months ago
vocab.json
2.78 MB
added model files
4 months ago
