A Bengali sentiment analysis model based on the Transformer architecture, fine-tuned on the SentiGOLD dataset, supporting 5-category sentiment analysis, and capable of effectively handling formal and informal texts, suitable for scenarios such as social media and reviews.

Natural Language ProcessingTransformersOther

A vision-language model fine-tuned on VQA datasets based on the ViLT-B32-MLM model

MultimodalTransformers

A model supporting style transfer translation for character dialogues in "BanG Dream!"

Natural Language ProcessingTransformersMultiple Languages

A financial domain sentiment analysis model fine-tuned based on econo-sentence-v2, achieving 96.2% accuracy on the Financial Phrase Bank dataset

Natural Language ProcessingTransformersEnglish

FocalCodec is a low bitrate speech codec based on focal modulation technology. It is designed for efficient compression of speech signals, which can significantly reduce the bitrate while maintaining high speech quality. This model is trained on the LibriTTS 960 dataset and provides 50Hz checkpoints for 16kHz and 24kHz sampling rates, suitable for speech communication and storage scenarios that require low bandwidth transmission.

Audio ProcessingSafetensors

This model is based on the transformers library, and its specific functions and uses require further information to determine.

Natural Language ProcessingTransformers

TIGER is a lightweight speech separation model that achieves efficient audio processing through frequency band segmentation and multi-scale feature extraction

Audio ProcessingSafetensorsEnglish

TIGER is a lightweight speech separation model that effectively extracts key acoustic features through frequency band partitioning, multi-scale, and full-band frame modeling.

Audio ProcessingSafetensorsEnglish

This model is fine-tuned based on mbart-large-50-many-to-many-mmt, specifically designed for converting Romanized Bengali to standard Bengali script

Natural Language ProcessingTransformers

NVIDIA NeMo Audio Codec 44khz is a neural audio codec that can compress audio into a quantized representation and can also be used as a vocoder for speech synthesis. This model is suitable for 44.1kHz full - bandwidth speech and supports speech data in 79 languages. Its performance may degrade on low - bandwidth speech or non - speech audio.

Audio ProcessingNemo

This is a BERT base model specifically pre-trained for the Bengali language. Based on the Transformer architecture, it has 110 million parameters. The model is trained with 36GB of Bengali text data and can effectively understand the contextual semantics of Bengali, supporting various natural language processing tasks.

Natural Language ProcessingTransformersOther

A FinTech chatbot fine-tuned based on T5-small architecture, specifically designed for banking inquiries

Natural Language ProcessingSafetensorsEnglish

AI virtual anchor BanBan model, a virtual anchor assistant designed specifically for the NTNU VLSI club, capable of image-text-to-text conversion.

MultimodalGgufMultiple Languages

This is a model specifically designed to detect personal data in documents. It can identify 12 common types of personal sensitive information, including names, addresses, phone numbers, ID card numbers, etc., to help users protect data privacy and conduct security reviews.

Natural Language ProcessingTransformers

BigVGAN is a high-performance neural vocoder that achieves high-quality audio generation through large-scale training, supporting multiple sample rates and frequency band configurations.

BigVGAN is a high-performance neural vocoder that achieves high-quality audio synthesis through large-scale training, supporting multiple sampling rates and frequency band configurations.

EBEN is a bandwidth extension model for French speech, specifically designed to process audio collected by body-conducted voice sensors (such as throat microphones). It can reduce noise in low-frequency, noisy body-conducted voice and regenerate mid- and high-frequency components from low-frequency content, thereby significantly improving the clarity and quality of the audio. This model is trained on specific non-traditional sensor data and is suitable for voice enhancement tasks in specific fields.

Audio ProcessingTransformersFrench

A line art portrait illustration generation model based on Stable Diffusion XL, excelling in creating impactful monochrome manga-style images

Computer VisionDiffusers

Kaviel is a text classification model fine-tuned based on roberta-base, specifically designed to classify text into six major threat categories: bank fraud, terrorist attacks, life threats, online scams, information leakage, and daily conversations, helping threat intelligence platforms automatically detect and manage threats.

Natural Language ProcessingTransformersEnglish

A banking-specific large language model fine-tuned based on Mistral-7B, focusing on banking transactions and customer support scenarios

Natural Language ProcessingTransformers