Borealis is the first automatic speech recognition (ASR) audio large language model for Russian, trained on approximately 7,000 hours of Russian audio data. This model supports the recognition of punctuation marks in audio. Its architecture is inspired by Voxtral but has been improved, and it performs excellently in multiple Russian ASR benchmark tests.

Audio ProcessingPytorchOther

Voxtral-Mini-3B-2507-FP8-dynamic is a quantized version of Voxtral-Mini-3B-2507, optimized for speech transcription, translation, and audio understanding, using the FP8 data type for quantization. This model has powerful audio understanding capabilities and can handle various audio-related tasks.

MultimodalSafetensorsMultiple Languages

This is a specific version of Voxtral-Mini-3B-2507 that removes the speech recognition function and only retains the pure language model function. This model is similar to the unreleased Ministral-3B-Instruct model and focuses on text generation tasks.

Natural Language ProcessingTransformers

Voxtral Mini is an enhanced version based on Ministral 3B, with advanced audio input capabilities and excellent performance in speech transcription, translation, and audio understanding.

MultimodalTransformersMultiple Languages