# Speech Recognition

Ultravox v0.5 is an audio-to-text model optimized from the Llama-3 2.1B architecture, focusing on efficient speech transcription tasks.

A speech recognition model fine-tuned from facebook/hubert-large-ls960-ft, trained on the LibriSpeech dataset

This model is a speech recognition model fine-tuned on the LibriSpeech dataset based on facebook/wav2vec2-base, achieving a word error rate of 0.3174 on the evaluation set.

A fine-tuned speech processing model based on facebook/wav2vec2-base, achieving 99.48% accuracy on the evaluation set

A speech processing model further fine-tuned based on wav2vec2-base-finetuned, achieving 98.82% accuracy on the evaluation set

A fine-tuned speech processing model based on wav2vec2-base-finetuned, achieving 98.82% accuracy on the evaluation set

A speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53, focusing on phoneme recognition tasks

A speech processing model fine-tuned based on the facebook/wav2vec2-base model, achieving 99.97% accuracy on the evaluation set

A speech processing model fine-tuned based on the facebook/wav2vec2-base model, achieving 99.97% accuracy on the evaluation set

An audio classification model fine-tuned on an audio folder dataset based on the wav2vec2-base model, achieving 99.82% accuracy on the validation set

This model is a dialect classifier based on the whisper-small architecture, designed to recognize and classify speech inputs of specific dialects.

A speech processing model fine-tuned based on facebook/wav2vec2-base, demonstrating excellent performance on the evaluation set

This model is a fine-tuned audio classification model based on facebook/wav2vec2-base on the superb dataset, achieving 99.87% accuracy on the evaluation set.

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset, primarily used for speech recognition tasks, achieving an accuracy of 84.55% on the evaluation set.

This model is a fine-tuned audio classification model based on facebook/wav2vec2-base on the superb dataset, achieving an accuracy of 0.6578 on the evaluation set.

A speech recognition model fine-tuned on the superb dataset based on facebook/wav2vec2-base, achieving 98.34% accuracy

A small speech recognition model based on the Whisper architecture, suitable for domain-specific speech-to-text tasks

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-xls-r-300m, primarily used for English speech-to-text tasks.

This model is a speech recognition model fine-tuned on the SUPERB dataset based on facebook/wav2vec2-base, demonstrating excellent performance in keyword spotting tasks.

A fine-tuned version based on facebook/wav2vec2-base model for specific tasks

A speech recognition model fine-tuned based on facebook/wav2vec2-base, achieving an accuracy of 87.27% on the evaluation set.

This model is a fine-tuned version of facebook/wav2vec2-base, primarily used for speech recognition tasks.

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

A speech recognition model fine-tuned on the TIMIT dataset based on the facebook/wav2vec2-base model, featuring a low Word Error Rate (WER).

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

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

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base on the Common Voice 3.0 English dataset, achieving a word error rate of 0.247 on the test set.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, achieving a word error rate of 0.1042 on the evaluation set.

A speech recognition model fine-tuned based on facebook/wav2vec2-base-960h

A speech recognition model fine-tuned based on facebook/wav2vec2-base-960h, achieving a word error rate of 1.0 on the evaluation set

A speech recognition model fine-tuned based on facebook/wav2vec2-base, achieving a word error rate (WER) of 0.3355 on the evaluation set.

This is a speech recognition model fine-tuned on the superb dataset based on distilhubert, primarily used for Automatic Speech Recognition (ASR) tasks.

This is an automatically generated test model, primarily for demonstration and experimental purposes.

This model is a speech recognition model fine-tuned on the TIMIT dataset based on facebook/wav2vec2-base, achieving a word error rate (WER) of 0.3384 on the evaluation set.

A speech keyword detection model based on the wav2vec2 architecture, optimized with Optimum OpenVINO quantization

A speech recognition model fine-tuned based on facebook/wav2vec2-base, achieving a word error rate of 0.3417 on the evaluation set.

This model is a speech recognition model fine-tuned on the Common Voice dataset based on facebook/wav2vec2-xls-r-300m, supporting automatic speech recognition tasks.

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

A speech recognition model fine-tuned based on facebook/wav2vec2-base, achieving a word error rate of 0.4499 on the evaluation set

A speech recognition model fine-tuned based on facebook/wav2vec2-base, achieving a word error rate of 0.4499 on the evaluation set, which can be reduced to 0.126 when using a 4-Gram language model