Vikhr Salt is a multimodal model based on a pre-trained large language model, extended with new audio tokens to handle both TTS (text-to-speech) and ASR (automatic speech recognition) tasks. The model incorporates two variants for encoding audio—Encodec and SpeechTokenizer—and achieves stable training by fine-tuning precision settings. This approach allows Vikhr Salt to leverage pre-existing LLM knowledge while effectively generating and understanding speech, marking a step forward in multimodal learning.
Model Authors
Ksenya Sycheva, Konstantin Korolev, Aleksandr Nikolic
Runs of Vikhrmodels salt-116k on huggingface.co
45
Total runs
0
24-hour runs
0
3-day runs
-1
7-day runs
-18
30-day runs
More Information About salt-116k huggingface.co Model
salt-116k huggingface.co is an AI model on huggingface.co that provides salt-116k's model effect (), which can be used instantly with this Vikhrmodels salt-116k model. huggingface.co supports a free trial of the salt-116k model, and also provides paid use of the salt-116k. Support call salt-116k model through api, including Node.js, Python, http.
salt-116k huggingface.co is an online trial and call api platform, which integrates salt-116k's modeling effects, including api services, and provides a free online trial of salt-116k, you can try salt-116k online for free by clicking the link below.
Vikhrmodels salt-116k online free url in huggingface.co:
salt-116k is an open source model from GitHub that offers a free installation service, and any user can find salt-116k on GitHub to install. At the same time, huggingface.co provides the effect of salt-116k install, users can directly use salt-116k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.