# 16kHz sampling rate

This is an Icelandic text-to-speech model fine-tuned based on facebook/mms-tts-isl, trained using the Talrómur dataset, specializing in female voice synthesis.

This model is a Japanese speech recognition model fine-tuned based on openai/whisper-small, supporting Japanese speech-to-text tasks.

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

A Persian automatic speech recognition model fine-tuned from facebook/hubert-large-ll60k, trained using the Common Voice 7.0 Persian dataset.

This is a Swedish automatic speech recognition model fine-tuned based on the facebook/wav2vec2-large-nl-voxpopuli model, trained using the Common Voice 7.0 (sv-SE) dataset.

A Swedish automatic speech recognition model fine-tuned from microsoft/wavlm-large, suitable for 16kHz sampled audio input.

A French automatic speech recognition model fine-tuned based on the facebook/wav2vec2-large-fr-voxpopuli model, trained using the Common Voice 7.0 French dataset.

A speech recognition model fine-tuned using the Common Voice 7.0 (French) dataset, based on the microsoft/unispeech-large-1500h-cv model

Fine-tuned from a randomly initialized wav2vec2 model for Italian speech recognition tasks, trained on the training split of Common Voice 7.0 (Italian).

An Italian automatic speech recognition model fine-tuned based on the facebook/wav2vec2-large-xlsr-53 model, trained using the Common Voice 7.0 Italian dataset.

An Italian automatic speech recognition model fine-tuned from the facebook/wav2vec2-large-100k-voxpopuli model, trained using the Common Voice 7.0 Italian dataset.

An Italian automatic speech recognition model fine-tuned based on facebook/wav2vec2-large-lv60, trained using the Common Voice 7.0 Italian dataset.

A Thai speech recognition model fine-tuned from facebook/hubert-large-ll60k, trained on data from Common Voice 7.0

A Thai speech recognition model fine-tuned based on facebook/wav2vec2-large-lv60, trained using the Common Voice 7.0 dataset

An English speech recognition model fine-tuned based on facebook/wav2vec2-large-nl-voxpopuli, trained using the Common Voice 7.0 training set.

This is a model designed for English speech recognition tasks, based on a randomly initialized wav2vec2 architecture and fine-tuned using the Common Voice 7.0 dataset.

A fine-tuned version of Sharif Wav2vec2 for Persian language, trained on Common Voice Persian samples, supporting automatic speech recognition tasks.

Data2Vec is a general self-supervised learning framework applicable to speech, vision, and language tasks. This large audio model is pre-trained and fine-tuned on 960 hours of LibriSpeech data, specifically optimized for automatic speech recognition tasks.

Danish speech recognition model fine-tuned on the NST dataset, supporting 16kHz sampled audio input

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

A Hindi automatic speech recognition model fine-tuned on low-resource Indian language datasets based on facebook/wav2vec2-large-xlsr-53

This is a Slovenian automatic speech recognition model fine-tuned from Facebook's wav2vec2-large-xlsr-53 model, trained on the Common Voice dataset with a word error rate of 36.04%.

This is a Kazakh automatic speech recognition (ASR) model fine-tuned from facebook/wav2vec2-large-xlsr-53, trained on the Kazakh speech corpus v1.1 with a test WER of 19.65%.

Vietnamese speech recognition model based on Wav2Vec2 architecture, fine-tuned on VSLP dataset, supports 16kHz sampled speech input

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

A Basque automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, achieving a 15.34% word error rate (WER) on the Common Voice Basque test set.

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

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

This is an Italian automatic speech recognition model based on the XLS-R 1B architecture, fine-tuned on multiple Italian datasets

A Javanese automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, trained on high-quality Javanese TTS data from OpenSLR.

A Sundanese speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, trained on high-quality TTS data from OpenSLR

Fine-tuned automatic speech recognition model based on facebook/wav2vec2-large-xlsr-53 on the English Common Voice dataset, supporting punctuation prediction

This is a Polish automatic speech recognition (ASR) model fine-tuned based on the XLS-R 1-billion parameter model, trained on datasets such as Common Voice 8.0, supporting 16kHz sampling rate audio input.

A Turkish speech recognition model fine-tuned on the Common Voice dataset based on Facebook's wav2vec2-large-xlsr-53 model

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

A Khmer speech recognition model fine-tuned on the facebook/wav2vec2-large-xlsr-53 model, achieving a WER of 24.96% on the OpenSLR Khmer dataset.

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

This is an automatic speech recognition model fine-tuned on the Indonesian common voice dataset based on facebook/wav2vec2-large-xlsr-53, supporting Indonesian speech recognition.

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

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