# Multi-emotion Classification

A speech emotion recognition model based on Whisper-Large V3, optimized for the MSP-Podcast dataset, supporting 9 emotion classifications

This is a fine-tuned model based on Audio Spectrogram Transformer (AST), specifically designed for emotion classification in speech audio.

A German emotion classification model fine-tuned based on RoBERTa, capable of classifying text into six emotion categories: anger, fear, disgust, sadness, happiness, and none of the above.

XLM-RoBERTa-based German emotion classification model capable of recognizing 28 emotions

This model uses a fine-tuned wav2vec2 (base) architecture, trained on the IEMOCAP dataset for speech emotion recognition tasks.

This model is used to recognize six basic emotions from English audio: anger, disgust, fear, happiness, sadness, and surprise, trained on the RAVDESS dataset.

A baseline model for speech emotion recognition based on the WavLM architecture, designed to predict 8 basic emotion categories

A fine-tuned Arabic speech emotion recognition model based on facebook/wav2vec2-base, achieving 99.92% accuracy on the evaluation dataset.

Emollama-7b is the first open-source large language model series EmoLLMs with instruction-following capability, fine-tuned based on LLaMA2-7B for comprehensive sentiment analysis

A Japanese sentiment analysis model fine-tuned from Luke-japanese-large-lite, capable of identifying eight types of emotions in text

A German speech emotion detection model based on wav2vec2, trained on the emo-DB dataset, capable of recognizing 7 different emotions.

A sentiment analysis model based on the IndoBERT pre-trained model for predicting six types of emotions in Indonesian sentences.

This is a Transformer-based emotion classification model capable of identifying 32 different emotions in input text.

A fine-tuned Urdu audio emotion classification model based on facebook/wav2vec2-large-xlsr-53, supporting recognition of four emotions: anger, happiness, calmness, and sadness.

This is a Russian speech emotion recognition model based on the XLS-R Wav2Vec2 architecture, capable of identifying 7 basic emotions with an accuracy of 72%.

A financial social media sentiment analysis model fine-tuned on DistilBERT, specialized in analyzing text sentiment from platforms like StockTwits

HeBERT is a pre-trained language model for Hebrew, focusing on polarity analysis and sentiment recognition tasks.

This is a Persian speech emotion recognition model based on the Wav2Vec 2.0 architecture, capable of identifying six basic emotional states.

A lightweight sentiment analysis model based on DistilBERT, retaining 97% of BERT's language understanding capability through knowledge distillation, with a 40% smaller size and faster inference speed.

This is an emotion recognition model based on the Wav2Vec2-Large model, specifically designed to identify emotion categories from speech.

This model is fine-tuned from Google's T5-base model on an emotion recognition dataset, designed for text sentiment classification tasks, capable of classifying text into 6 basic emotions.

A speech emotion recognition model based on the XLSR-Wav2Vec architecture, capable of identifying five basic emotions: anger, disgust, fear, happiness, and sadness.

A Greek speech emotion recognition model based on the Wav2Vec 2.0 architecture, capable of identifying five emotions: anger, disgust, fear, happiness, and sadness.

This model is an emotion recognition model based on the Hubert-Base architecture, trained on the SUPERB emotion recognition task for speech emotion classification

A speech emotion recognition model fine-tuned on Wav2Vec 2.0, capable of identifying 8 English emotions with an accuracy of 82.23% on the RAVDESS dataset

An emotion recognition model based on Hubert-Large pre-trained model for predicting emotion categories in speech

This is a French sentiment analysis model based on FlauBERT, capable of detecting four types of emotions in text: mixed, negative, neutral, and positive.

A tool for sentiment and emotion classification in Italian, supporting four basic emotions: anger, fear, happiness, and sadness

A Danish BERT-based text emotion classification model that categorizes Danish text into 8 emotion categories