# 16kHz audio adaptation

This model is a Wav2Vec2 base model pre-trained on 3,000 hours of Vietnamese speech data, suitable for Vietnamese speech recognition tasks, and requires fine-tuning on downstream tasks for use.

Data2Vec is a general self-supervised learning framework applicable to speech, natural language processing, and computer vision tasks. This model is a large-scale model pre-trained and fine-tuned on 100 hours of Librispeech audio data.

A multilingual speech recognition model based on the wav2vec 2.0 architecture, specifically fine-tuned for Persian, significantly reducing word error rate

This is an automatic speech recognition (ASR) model fine-tuned on the Estonian Common Voice dataset, based on the facebook/wav2vec2-large-xlsr-53 model.

Speech model based on Facebook's Wav2Vec2 architecture, pre-trained on the Croatian VoxPopuli corpus

A Breton fine-tuned speech recognition model based on facebook/wav2vec2-large-xlsr-53

This is a Hungarian automatic speech recognition model fine-tuned from the facebook/wav2vec2-large-xlsr-53 model, trained using the Common Voice dataset.

A speech recognition model fine-tuned on the Common Voice Japanese dataset based on facebook/wav2vec2-large-xlsr-53

Wav2Vec2 is a powerful speech recognition model that extracts features from raw audio through self-supervised learning and achieves high-performance speech recognition with limited labeled data.

Georgian automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampled audio input

A Chuvash automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, trained on the Common Voice dataset with a word error rate of 40.01%.

This is a fine-tuned XLSR-53 large model for German speech recognition tasks, based on Facebook's wav2vec2-large-xlsr-53 model and fine-tuned on the Common Voice 6.1 German dataset.

A speech recognition model fine-tuned with approximately 270 hours of Vietnamese annotated data, supporting Vietnamese automatic speech recognition tasks

A speech classification model fine-tuned on the SUPERB keyword spotting task, based on the Wav2Vec2-Large-LV60 pre-trained model

An automatic speech recognition model fine-tuned for Estonian using the Common Voice dataset, based on facebook/wav2vec2-large-xlsr-53

A speech model based on Facebook's Wav2Vec2 architecture, specifically pre-trained for Danish using 13.6k unlabeled data from the VoxPopuli corpus.

Estonian speech recognition model fine-tuned from Facebook's XLSR-53 large model, achieving 30.74% word error rate on Common Voice dataset

A Tamil speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, trained on the Common Voice Tamil dataset.

A Spanish speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, trained on the Common Voice 6.1 Spanish dataset

Facebook's Wav2Vec2 large model, pretrained exclusively on 66.3 hours of unlabeled data from the West Germanic VoxPopuli corpus.

Greek speech recognition model pretrained on VoxPopuli corpus using 17.7 hours of unlabeled data

SEW-D is a compressed and efficient speech pre-training model developed by ASAPP Research, pre-trained on 16kHz sampled speech audio, suitable for various downstream speech tasks.

An automatic speech recognition model fine-tuned on the Common Voice Mongolian dataset based on facebook/wav2vec2-large-xlsr-53

A French speech recognition model fine-tuned from facebook/wav2vec2-large-fr-voxpopuli, trained on the Common Voice 6.1 French dataset, supporting 16kHz audio input

Yakut speech recognition model fine-tuned from XLSR-53 large model, with 32.23% word error rate

A Vietnamese automatic speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampling rate audio input.

Vietnamese automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53

A Lithuanian speech recognition model fine-tuned from Facebook's XLSR-53 large model, trained on the Common Voice dataset with a test WER of 56.55%.