# Multilingual speech translation

Ultravox is a large multimodal speech language model capable of understanding and processing speech input, supporting multiple languages and noisy environments.

Phi-4-multimodal-instruct is a lightweight open-source multimodal foundation model that integrates language, vision, and speech research and datasets from Phi-3.5 and 4.0 models. It supports text, image, and audio inputs to generate text outputs, with a context length of 128K tokens.

SeamlessM4T is a large-scale multilingual multimodal machine translation model supporting speech and text translation in nearly 100 languages.

SeamlessM4T v2 is a large-scale multilingual multimodal machine translation model released by Facebook, supporting speech and text translation for nearly 100 languages.

Facebook's Wav2Vec2 XLS-R model for multilingual speech-to-English translation tasks.

Transformer-based end-to-end multilingual speech translation model supporting English-to-multiple language speech translation

Facebook's Wav2Vec2 XLS-R model for multilingual speech-to-English translation tasks

Facebook's Wav2Vec2 XLS-R fine-tuned for speech translation from 21 languages to English

Facebook's Wav2Vec2 XLS-R model fine-tuned for speech translation tasks, supporting translation from English to 15 target languages.

Facebook's Wav2Vec2 XLS-R model, fine-tuned for speech translation tasks in 15 languages, capable of translating spoken English into multiple written languages.

Facebook's Wav2Vec2 XLS-R model fine-tuned for multilingual speech translation tasks, supporting translation from English to 15 target languages.