# Wav2Vec2 Architecture

Hindi automatic speech recognition (ASR) model based on Wav2Vec2 architecture, developed by AI4Bharat

An audio classification model fine-tuned based on facebook/wav2vec2-base-960h, with specific uses and training data not clearly specified.

This is a fine-tuned model for speech language identification (LID) across 512 languages, based on the Wav2Vec2 architecture, capable of recognizing the language category of input audio.

This is a speech language identification model based on the Wav2Vec2 architecture, capable of recognizing 256 languages, and is part of Facebook's Massively Multilingual Speech (MMS) project.

A language identification model fine-tuned from Facebook's Massively Multilingual Speech project, supporting audio classification for 126 languages

A Chinese speech model pretrained on 10,000 hours of WenetSpeech L subset, suitable for speech-related tasks

A fine-tuned speech recognition model based on facebook/wav2vec2-base, supporting automatic speech-to-text tasks.

A speech recognition model fine-tuned from facebook/wav2vec2-base, achieving a Word Error Rate (WER) of 1.0 on the evaluation set

This is a Russian speech emotion recognition model based on the XLS-R Wav2Vec2 architecture, capable of identifying 7 basic emotions with an accuracy of 72%.

A fine-tuned speech recognition model based on facebook/wav2vec2-base with a Word Error Rate (WER) of 1.0

This model is a speech recognition model fine-tuned based on facebook/wav2vec2-base-960h, achieving a word error rate (WER) of 1.0 on the evaluation set.

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on Filipino speech datasets, primarily used for English-to-Filipino speech recognition tasks.

A speech recognition model fine-tuned on the TIMIT dataset based on the facebook/wav2vec2-base model

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, trained and evaluated on the TIMIT dataset.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, trained for 60 epochs on the TIMIT dataset with a word error rate (WER) of 1.0.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, trained on the TIMIT dataset with a Word Error Rate (WER) of 0.5426.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, trained on the TIMIT dataset with an evaluated word error rate of 0.5608.

This model is a speech recognition model fine-tuned from facebook/wav2vec2-base, achieving a word error rate (WER) of 0.5664 on the evaluation set.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, trained on the TIMIT dataset with a word error rate (WER) of 0.5282.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base on the TIMIT dataset, primarily used for English speech-to-text tasks.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, trained on the TIMIT dataset with a Word Error Rate (WER) of 1.0.

A speech recognition model fine-tuned based on facebook/wav2vec2-base, achieving a 31.38% word error rate on the evaluation set

A speech recognition model fine-tuned on an unknown dataset based on facebook/wav2vec2-base, with a Word Error Rate (WER) of 0.7175

This is a Turkish automatic speech recognition model based on the XLSR Wav2Vec2 architecture, trained on the Common Voice Turkish dataset.

A speech recognition model fine-tuned on the TIMIT dataset based on the facebook/wav2vec2-base model

This is an Indonesian automatic speech recognition model based on the XLSR Wav2Vec2 architecture, developed by cahya and fine-tuned on the Common Voice Indonesian dataset.

A base Wav2Vec2 model pretrained on 100 hours of unlabeled Vietnamese speech audio from the VLSP dataset, requiring fine-tuning for downstream tasks.

A Hindi speech recognition model based on the Wav2Vec2 architecture that directly transcribes audio into text.

A Greek speech emotion recognition model based on the Wav2Vec 2.0 architecture, capable of identifying five emotions: anger, disgust, fear, happiness, and sadness.

XLS-R-300M is an English automatic speech recognition model fine-tuned on the librispeech_asr dataset based on facebook/wav2vec2-xls-r-300m, achieving a word error rate of 12.29% on the LibriSpeech test set.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, trained on the TIMIT dataset with an evaluation set word error rate (WER) of 0.3874.

A speech recognition model fine-tuned on the TIMIT dataset based on the facebook/wav2vec2-base model

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base-960h, achieving a word error rate of 21.61% on the evaluation set.

A speech recognition model fine-tuned on the TIMIT dataset based on facebook/wav2vec2-large-lv60, using 5% of the data for supervised training

A speech recognition model fine-tuned on the TIMIT dataset based on the facebook/wav2vec2-base model, specializing in English speech-to-text tasks.

An Urdu automatic speech recognition (ASR) model fine-tuned from Facebook's wav2vec2-xls-r-1b model, trained on the Common Voice 8.0 Urdu dataset