Step-Audio LLM is the industry’s first 130-billion parameter hu-manlike unified end-to-end model that integrates multimodal speech un-derstanding and generation capabilities, including singing voice synthesis, tool utilization, role-play and multilingual/dialectal comprehension and synthesis.
This repository provides the speech tokenizer component of Step-Audio LLM. For linguistic tokenization, we utilize the output from the Paraformer encoder, which is quantized into discrete representations at a token rate of 16.7 Hz. For semantic tokenization, we employ CosyVoice’s tokenizer, specifically designed to efficiently encode features essential for generating natural and expressive speech outputs, operating at a token rate of 25 Hz.
More information
For more information, please refer to our repository:
Step-Audio
.
Runs of stepfun-ai Step-Audio-Tokenizer on huggingface.co
0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About Step-Audio-Tokenizer huggingface.co Model
Step-Audio-Tokenizer huggingface.co is an AI model on huggingface.co that provides Step-Audio-Tokenizer's model effect (), which can be used instantly with this stepfun-ai Step-Audio-Tokenizer model. huggingface.co supports a free trial of the Step-Audio-Tokenizer model, and also provides paid use of the Step-Audio-Tokenizer. Support call Step-Audio-Tokenizer model through api, including Node.js, Python, http.
Step-Audio-Tokenizer huggingface.co is an online trial and call api platform, which integrates Step-Audio-Tokenizer's modeling effects, including api services, and provides a free online trial of Step-Audio-Tokenizer, you can try Step-Audio-Tokenizer online for free by clicking the link below.
stepfun-ai Step-Audio-Tokenizer online free url in huggingface.co:
Step-Audio-Tokenizer is an open source model from GitHub that offers a free installation service, and any user can find Step-Audio-Tokenizer on GitHub to install. At the same time, huggingface.co provides the effect of Step-Audio-Tokenizer install, users can directly use Step-Audio-Tokenizer installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Step-Audio-Tokenizer install url in huggingface.co: