Voice: speakers and sound

Эмоции в русской речи (модели на датасете Dusha)

Models that detect emotion from voice in Russian speech: neutral, anger, positive, sadness. Trained on the open Dusha dataset from SberDevices.

Developer
Community (xbgoose and others), Dusha dataset from SberDevices, Russia
First release
May 2023
Latest release
Jul 2025
Sizes
21M – 316M
License
Commercial use with conditionsApache 2.0 for HuBERT-large; for the other versions the license is not stated on the model card
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Marketing and content
Deploy on your server Hugging Face GitHub

What it does

  • Finding calls with irritated customers
  • Assessing the tone of operator conversations
  • Prioritizing complaints in a call center

Where it is used

Call centersService quality control

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Whisper-base SER Dusha
  2. HuBERT-base и WavLM Dusha
  3. HuBERT-large Dusha

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Эмоции в русской речи (модели на датасете Dusha) be used in a commercial project?

With conditions. License: Apache 2.0 for HuBERT-large; for the other versions the license is not stated on the model card. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Эмоции в русской речи (модели на датасете Dusha) need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Эмоции в русской речи (модели на датасете Dusha) support Russian?

Yes, Russian is listed on the model card.

Where can I download Эмоции в русской речи (модели на датасете Dusha) and what does it cost?

The Эмоции в русской речи (модели на датасете Dusha) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Speech to textGigaAMSber · RussiaCommercial use allowed

Sber's models for Russian speech recognition, among the most accurate for Russian. Includes emotion recognition, v3 with punctuation, and a multilingual version (Russian, Kazakh, Kyrgyz, Uzbek).

DetailsSpeech to textSenseVoice / Paraformer / Fun-ASRAlibaba (Tongyi, FunAudioLLM) · ChinaCommercial use with conditions

Alibaba's set of fast speech recognition models, primarily for Chinese and Asian languages. SenseVoice also detects emotions and sound events.

Details

Source: huggingface.co/waveletdeboshir/whisper-base-ser-dusha. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.