# Multilingual ASR

A localized Vietnamese-enhanced version of Whisper Large-v3 Turbo optimized with CTranslate2, supporting multilingual speech recognition with high speed and accuracy

A Whisper Large-v3 Turbo speech recognition model optimized for Vietnamese, supporting real-time transcription in multiple languages

Lite-Whisper is a lightweight version of OpenAI Whisper compressed using LiteASR technology, significantly reducing model size while maintaining high accuracy.

A Tajik automatic speech recognition model fine-tuned from OpenAI Whisper-small, trained on Google Fleurs dataset with a word error rate of 24.26%.

WhisperKit is a local speech recognition framework specifically designed for Apple chips, offering efficient automatic speech recognition capabilities.

Whosper-large-v2 is a cutting-edge speech recognition model specifically designed for Wolof, the primary language of Senegal. Built upon OpenAI's Whisper-large-v2, it significantly improves Word Error Rate (WER) and Character Error Rate (CER).

WhisperKit Pro is the commercial version of WhisperKit, focusing on automatic speech recognition (ASR) tasks, supporting quantization technology for efficient speech processing.

CrisperWhisper is an advanced variant of OpenAI Whisper, designed for fast, precise, and word-for-word speech recognition, providing accurate (clear) word-level timestamps.

WhisperKit is a local speech recognition framework optimized for Apple Silicon, supporting efficient automatic speech recognition tasks.

Whisper is a pre-trained automatic speech recognition (ASR) and speech translation model, trained on 680,000 hours of labeled data, demonstrating strong generalization capabilities. This repository contains the INT4 weight-only quantized version of the Whisper large v2 model in ONNX format.

This is a speech recognition model fine-tuned on the Catalan Common Voice 11.0 dataset based on OpenAI Whisper Medium.

This is an automatic speech recognition model fine-tuned on Hausa speech data based on facebook/wav2vec2-xls-r-300m

This is an automatic speech recognition (ASR) model fine-tuned on the Lithuanian Common Voice 7.0 dataset, based on the facebook/wav2vec2-xls-r-300m model.

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice dataset, supporting Guarani speech recognition.

Hindi speech recognition model fine-tuned from facebook/wav2vec2-xls-r-300m, trained on Openslr multilingual corpus and Common Voice 7.0 dataset