# Multilingual speech recognition

A multilingual speech recognition model fine-tuned based on Whisper-base, supporting International Phonetic Alphabet (IPA) output

NVIDIA NeMo Canary Flash is a family of multilingual multitask models that achieves state-of-the-art performance across multiple speech benchmarks. Supports automatic speech recognition and translation tasks in four languages.

This is the CTranslate2 converted version of OpenAI's Whisper-large-v3-turbo model, employing INT8 quantization technology, primarily designed for efficient speech recognition tasks.

A pre-trained Conformer encoder model based on self-supervised learning, supporting automatic speech recognition tasks for 22 scheduled Indian languages.

A distilled multilingual Whisper model supporting automatic speech recognition for 7 European languages with code-switching capability

Whisper large-v3-turbo is a distilled version of OpenAI Whisper large-v3, with the decoder layers reduced from 32 to 4, significantly improving speed while slightly reducing quality.

Whisper is a Transformer-based encoder-decoder model for speech recognition and translation tasks, supporting multilingual processing.

A fine-tuned multilingual speech classification model based on Whisper-small, supporting speech recognition and classification for Uzbek, English, and Russian.

OWSM-CTC is an encoder-only speech foundation model based on hierarchical multi-task self-conditioned CTC, supporting multilingual speech recognition, speech translation, and language identification.

This is a CTranslate2 converted version of the OpenAI Whisper large-v3 model, specifically fine-tuned for Japanese with an additional 4,000 training steps, supporting multilingual speech recognition.

Canary-1B is a multilingual multi-task model developed by NVIDIA NeMo, supporting automatic speech recognition and speech translation tasks in English, German, French, and Spanish.

A speech recognition model fine-tuned on the Common Voice 16.0 dataset based on OpenAI Whisper Large V3

An improved multilingual automatic speech recognition model based on whisper-small, enhancing target language performance through CLSR module and knowledge distillation

CTranslate2 converted version of OpenAI Whisper tiny model for efficient speech recognition

This is the CTranslate2 converted version of OpenAI's Whisper base model, designed for efficient speech recognition tasks.

This is the CTranslate2 converted version of OpenAI's Whisper medium model, designed for efficient speech recognition tasks.

Whisper large-v3 is a large-scale multilingual automatic speech recognition (ASR) model developed by OpenAI, supporting speech-to-text tasks in multiple languages.

Whisper is an advanced automatic speech recognition (ASR) and speech translation model proposed by OpenAI, trained on over 5 million hours of labeled data, with strong cross-dataset and cross-domain generalization capabilities.

ECAPA-TDNN based spoken language identification model trained on VoxLingua107 dataset, supporting classification of 107 languages

This is the CTranslate2 converted version of the OpenAI Whisper large-v1 model for efficient speech recognition tasks

This is the CTranslate2 converted version of OpenAI Whisper large-v2 model for efficient speech recognition

This project converts the openai/whisper-medium model to the CTranslate2 model format, which can be used for efficient speech recognition.

The Whisper base model is an Automatic Speech Recognition (ASR) model developed by OpenAI, supporting speech-to-text tasks in multiple languages.

This model is a speech recognition model fine-tuned on the Common Voice 11.0 Slovenian dataset based on OpenAI's Whisper Large-V2 model, with a word error rate of 13.83%.

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

A speech recognition model fine-tuned on mixed-language datasets based on Facebook's wav2vec2-xls-r-300m model, supporting Malay, Singaporean English, and Mandarin.

A fine-tuned speech recognition model based on facebook/wav2vec2-large-xlsr-53, supporting multilingual speech-to-text tasks

Armenian automatic speech recognition model based on wav2vec2-xls-r-2b architecture, supporting hy/hye language

A Transformer-based end-to-end speech translation model specifically designed for French-to-English speech translation tasks.

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the GOOGLE/XTREME_S - FLEURS.ALL dataset for multilingual speech recognition tasks.

A multilingual speech recognition model fine-tuned on the GOOGLE/XTREME_S - MINDS14.ALL dataset based on facebook/wav2vec2-xls-r-300m

A Polish speech recognition model fine-tuned on the GOOGLE/XTREME_S - MLS.PL dataset based on facebook/wav2vec2-xls-r-300m

A foundational speech recognition model pretrained on 10,000 hours of unlabeled data from the VoxPopuli corpus, supporting multilingual speech processing

This model is a speech recognition model fine-tuned on the common_voice dataset based on facebook/wav2vec2-large-xlsr-53, primarily used for robust speech event recognition.

Facebook's Wav2Vec2 large model, pretrained exclusively on unlabeled data from the VoxPopuli corpus for Maltese (mt), suitable for speech recognition tasks.

A speech recognition base model pretrained on 100,000 hours of unannotated data from the VoxPopuli corpus

A speech recognition model pre-trained on 100,000 hours of unlabeled data from the VoxPopuli corpus, supporting multilingual speech representation learning

This is an automatic speech recognition model based on the wav2vec2 architecture, specifically optimized for the Tamil language and supporting Nepali speech recognition tasks.

An audio pre-training model based on self-supervised learning, capable of learning cross-lingual speech representations from raw audio of 23 Indian languages

This is an automatic speech recognition model based on a sequence-to-sequence architecture, capable of converting speech into text.