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

A speech recognition model fine-tuned on the Common Voice 17.0 Swahili dataset based on OpenAI Whisper Large v2, designed specifically for the Swahili speech recognition task of the Tanzanian children's helpline. It has a significant improvement in Swahili recognition accuracy compared to the base model.

Audio ProcessingTransformersOther

Breeze ASR 25 is an advanced automatic speech recognition model fine-tuned based on Whisper-large-v2, specifically optimized for the recognition ability in Taiwan Mandarin and Mandarin-English code-switching scenarios.

Audio ProcessingSafetensorsMultiple Languages

Whisper is a pre-trained automatic speech recognition (ASR) and speech translation model, trained on 680,000 hours of annotated data with strong generalization capabilities.

Audio ProcessingSafetensorsMultiple Languages

Whisper is OpenAI's state-of-the-art automatic speech recognition (ASR) and speech translation model, trained on over 5 million hours of labeled data with strong zero-shot generalization capabilities. The Turbo version is a pruned and fine-tuned variant of the original, reducing decoder layers from 32 to 4, significantly improving speed with a slight quality trade-off.

Audio ProcessingTransformersMultiple Languages

Whisper is OpenAI's state-of-the-art automatic speech recognition (ASR) and speech translation model, supporting multiple languages

Audio ProcessingSafetensorsMultiple Languages

NVIDIA Parakeet TDT 0.6B V2 is a model based on automatic speech recognition (ASR) tasks, suitable for English speech-to-text tasks.

Audio ProcessingOnnxEnglish

This model is a Japanese automatic speech recognition (ASR) model based on the FastConformer architecture, developed by NVIDIA and converted to MLX format.

Audio ProcessingMlx

Granite-speech-3.3-2b is a compact and efficient speech language model developed by IBM, designed specifically for Automatic Speech Recognition (ASR) and Automatic Speech Translation (AST). It uses a two-pass design to improve modularity and security.

Audio ProcessingTransformersEnglish

GigaAM v2 is an automatic speech recognition (ASR) model that supports Russian speech-to-text tasks, offering both CTC and RNN-T architectures.

Audio ProcessingOnnxOther

KinyaWhisper is a fine-tuned Kinyarwanda automatic speech recognition (ASR) system based on OpenAI's Whisper model, specifically designed for low-resource indigenous languages.

Audio ProcessingTransformersOther

A compact and efficient speech-language model designed for Automatic Speech Recognition (ASR) and Automatic Speech Translation (AST), featuring a two-stage design for processing audio and text

MultimodalTransformersEnglish

Distil-Whisper is a distilled version of the Whisper model, optimized for Automatic Speech Recognition (ASR) tasks, offering faster inference speeds.

Quantum_STT is an advanced automatic speech recognition (ASR) and speech translation model, trained with large-scale weak supervision, supporting multiple languages and tasks.

Audio ProcessingTransformersMultiple Languages

A Hausa speech recognition model fine-tuned from facebook/w2v-bert-2.0, trained on 500 hours of Hausa data with a word error rate of 7.47%

Audio ProcessingTransformers

GigaAM-v2-RNNT is a Russian automatic speech recognition (ASR) model based on the RNNT architecture, suitable for speech-to-text tasks.

Audio ProcessingTransformersOther

Granite-speech-3.2-8b is a compact and efficient speech language model specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).

Audio ProcessingTransformersEnglish

Currently the fastest Danish ASR model, a distilled version of hviske-v2, achieving approximately 4x speed improvement while maintaining the same accuracy.

GigaAM-v2-CTC is a Russian automatic speech recognition (ASR) model trained using the CTC loss function and can be utilized via the Hugging Face transformers library.

Audio ProcessingTransformersOther

A Korean automatic speech recognition (ASR) and speech translation (AST) model fine-tuned based on microsoft/Phi-4-multimodal-instruct, demonstrating excellent performance on the zeroth-korean and fleurs datasets.

MultimodalTransformersKorean