# High-precision speech transcription

Haitian Creole speech recognition model fine-tuned based on OpenAI Whisper-medium, focusing on high-accuracy transcription

This is a fine-tuned version of distil-whisper-large-v3, specifically designed for automatic speech recognition (ASR) of Brazilian Portuguese, trained by combining the Common Voice 16 dataset and a private dataset.

Rev's Reverb ASR model is trained on 200,000 hours of professionally transcribed English speech data, making it one of the most accurate open-source automatic speech recognition systems for English.

Portuguese-optimized Whisper Medium speech recognition model achieving 6.579 word error rate (WER) on Common Voice 11 dataset

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

An automatic speech recognition model fine-tuned based on wav2vec2-large-xlsr-53, specializing in singing voice recognition

This model is an automatic speech recognition (ASR) model based on the wav2vec2-large-xlsr-53 architecture, fine-tuned on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING2 dataset, primarily used for singing voice recognition tasks.

Automatic speech recognition model based on wav2vec2-large-xlsr-53, fine-tuned on the GARY109/AI_LIGHT_DANCE dataset

This model is an automatic speech recognition (ASR) model based on the wav2vec2-large-lv60 architecture, fine-tuned on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING dataset, primarily used for singing voice recognition tasks.

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

An automatic speech recognition (ASR) model trained on the LibriSpeech dataset for converting English speech to text

This model is a speech recognition model trained on the librispeech_asr dataset, achieving a word error rate (WER) of 2.0133 on the evaluation set.

This is an automatic speech recognition (ASR) model based on the wav2vec2 architecture, specifically fine-tuned for French, achieving a word error rate (WER) of 12.82% on the Common Voice French test set.