# Long text support

This is a model that supports Sanskrit text-to-speech conversion, particularly suitable for the speech synthesis of religious mantras and traditional texts.

PLaMo-Embedding-1B is a Japanese text embedding model developed by Preferred Networks, demonstrating outstanding performance in Japanese text embedding benchmarks

A Thai legal text retriever fine-tuned based on the bge-m3 model, focusing on the field of corporate and commercial law

A 2B-parameter chat and instruction model optimized for Spanish, supporting text generation, dialogue, and Q&A tasks

This is a BERT base model pretrained specifically for Tigrinya, trained for 40 epochs on a dataset of 40 million tokens.