This is a fine-tuned version of the HuBERT large model specialized for speech emotion recognition in Russian, trained on the Dusha dataset. It classifies audio into emotion categories and can be used via the Transformers pipeline for audio-classification tasks. The model is openly available on Hugging Face for researchers and developers working on Russian-language affective computing or voice analysis applications.
xbgoose/hubert-large-speech-emotion-recognition-russian-dusha-finetuned sits in PulseGate's Voice, TTS & speech category. Automatically detecting emotional states from Russian speech audio without manual annotation or custom model training. xbgoose/hubert-large-speech-emotion-recognition-russian-dusha-finetuned is an open-source project aimed at AI researchers and speech technology developers. The project is open source (Open Source). It runs on the web and API.
It is developed by xbgoose, and it first shipped in 2021. Development happens publicly on GitHub with 147 stars. Among its 4 catalogued features are audio classification, emotion recognition, and russian speech. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do