# English Speech Recognition

NVIDIA Parakeet TDT 0.6B V2 is a model based on automatic speech recognition (ASR) tasks, suitable for English speech-to-text tasks.

A small speech recognition model based on the OpenAI Whisper architecture, focused on English speech-to-text tasks.

A speech recognition model optimized for chess coordinate recognition, fine-tuned using nearly 2,500 English chess coordinate audio files

Moonshine is a series of automatic speech recognition (ASR) models developed by Useful Sensors, specifically designed for English speech transcription, excelling on resource-constrained platforms.

Whisper is a general-purpose speech recognition model trained by OpenAI. This model is based on large-scale weakly supervised training and supports speech transcription in multiple languages.

Distil-Whisper is a knowledge-distilled version of Whisper large-v3, focusing on English speech recognition, offering faster inference speeds while maintaining accuracy close to the original model.

An automatic speech recognition (ASR) model fine-tuned on the Common Voice 16.0 English dataset based on w2v-bert-2.0

Distil-Whisper is a distilled version of the Whisper model, 6x faster with 49% smaller size, achieving near 1% WER on out-of-distribution evaluation sets.

CTranslate2 converted version of OpenAI Whisper small.en model for efficient speech recognition

Distil-Whisper is a distilled version of the Whisper model, 6 times faster than the original, with a 49% reduction in size, while maintaining performance close to the original in English speech recognition tasks.

Distil-Whisper is a distilled version of the Whisper model, achieving 6x speedup and 49% size reduction with only a 1% WER difference on out-of-distribution evaluation sets.

ONNX format conversion of Facebook's wav2vec2-base-960h model, designed for Transformers.js, supporting browser-side speech recognition

Large-scale speech recognition model based on the wav2vec 2.0 architecture, supporting English speech-to-text conversion

An English speech recognition model fine-tuned based on Microsoft's UniSpeech-SAT-Large model, supporting 16kHz sampled audio input.

This model is a fine-tuned speech recognition model based on jonatasgrosman/wav2vec2-large-xlsr-53-english on the ascend dataset.

Wav2Vec2 is a self-supervised learning-based speech recognition model, pre-trained and fine-tuned on 960 hours of LibriSpeech audio data, supporting English speech transcription.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-xls-r-300m on the GOOGLE/XTREME_S - VOXPOPULI.EN dataset, supporting English speech-to-text tasks.

English speech recognition model fine-tuned on the timit_asr dataset for the ascend model

This is an automatic speech recognition (ASR) model trained on the LibriSpeech dataset, capable of converting English speech into text.

An automatic speech recognition model fine-tuned on the English Common Voice dataset based on facebook/wav2vec2-large-xlsr-53, supporting English speech input at 16kHz sampling rate.

This is a speaker verification model based on the Wav2Vec2 architecture, specifically designed for the speaker verification task in the SUPERB benchmark.

A speech recognition model fine-tuned on the timit_asr dataset based on facebook/wav2vec2-base, supporting 16kHz sampled audio input

This model is a fine-tuned English Automatic Speech Recognition (ASR) model based on facebook/wav2vec2-base, achieving a word error rate of 0.3397 on the evaluation set.

Automatic Speech Recognition (ASR) model trained on LibriSpeech dataset for converting English speech to text

Automatic speech recognition model based on the WavLM architecture, fine-tuned on the LibriSpeech CLEAN dataset (100 hours)

A speech recognition model fine-tuned on the TIMIT dataset based on facebook/wav2vec2-large-lv60, supporting 16kHz sampled speech input.

An automatic speech recognition model fine-tuned on the Common Voice dataset for English, based on facebook/wav2vec2-large, supporting 16kHz sampled audio input.

This model is a speech recognition model trained on the LibriSpeech ASR dataset, capable of converting speech to text.

A speech recognition model fine-tuned on the LIBRISPEECH_ASR-CLEAN dataset based on facebook/wav2vec2-large-lv60

Wav2Vec2 base version speech recognition model trained on 100 hours of LibriSpeech data

An English automatic speech recognition (ASR) model fine-tuned based on microsoft/wavlm-base, trained on the english_ASR - CLEAN dataset with a word error rate (WER) of 0.0773.

An English fine-tuned speech recognition model based on facebook/wav2vec2-large, using the Common Voice dataset, supporting 16kHz sampled audio input.

This model is an automatic speech recognition model fine-tuned on the TIMIT_ASR dataset based on microsoft/unispeech-large-1500h-cv, achieving a word error rate (WER) of 21.96% on the evaluation set.

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.