# Multilingual Speech Processing

Phi-4-multimodal-instruct is a lightweight open-source multimodal foundation model that supports text, image, and audio inputs to generate text outputs, with a context length of 128K tokens.

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on Filipino speech datasets, primarily used for English-to-Filipino speech recognition tasks.

This model is a fine-tuned Nepali speech recognition model based on facebook/wav2vec2-large-xlsr-53.

A Transformer-based end-to-end speech translation model for English-to-Turkish speech-to-text tasks

This is a Transformer-based end-to-end speech translation model specifically designed for converting English speech into Estonian text.

This is a Transformer-based end-to-end speech translation model specifically designed to translate English speech into Catalan text.