# Small batch training

XTTS is a text-to-speech model trained on a 40-hour dataset, supporting Russian and suitable for speech synthesis tasks in the legal domain.

A vision model based on the ViT architecture for detecting watermarks in images

A speech processing model fine-tuned based on facebook/wav2vec2-base, with an accuracy of 28.57%

Gerbil-A-32m is an A-grade model with 32 million parameters, trained on 640 million tokens, suitable for various natural language processing tasks.

A model fine-tuned based on klue/bert-base, with unspecified specific uses and training data

An image anti-counterfeiting detection model based on ViT architecture, achieving 70.88% accuracy after fine-tuning on an unknown dataset

A speech processing model fine-tuned based on facebook/wav2vec2-base, specific purpose not clearly stated

A model fine-tuned based on microsoft/deberta-v3-base, achieving an accuracy of 75.76% on the evaluation set

A speech recognition model fine-tuned from facebook/wav2vec2-base, trained on a toy dataset with 0.1 ratio data augmentation applied

This model is a fine-tuned version based on the GPT-2 architecture, with no specific training data or purpose explicitly stated.