# Low character error rate

A Korean automatic speech recognition (ASR) and speech translation (AST) model fine-tuned based on microsoft/Phi-4-multimodal-instruct, demonstrating excellent performance on the zeroth-korean and fleurs datasets.

A Cantonese automatic speech recognition model fine-tuned on Whisper v3, trained on the Common Voice 17 dataset

A handwriting recognition model fine-tuned from Microsoft's TrOCR, specialized for 19th-century Finnish and Swedish court record documents

A Ukrainian automatic speech recognition model trained on the mHuBERT-147 base model, supporting Ukrainian speech-to-text tasks.

A captcha OCR model fine-tuned based on microsoft/trocr-base-printed, designed to extract text from image captchas.

A Mongolian speech recognition model fine-tuned on Mongolian datasets based on OpenAI's whisper-large-v2 model, supporting automatic speech recognition tasks in Mongolian.

A Cantonese automatic speech recognition (ASR) model fine-tuned based on OpenAI Whisper Large V2, trained on the Common Voice 11.0 Cantonese dataset with a character error rate (CER) of 6.21%.

A Chinese speech recognition model fine-tuned on the google/fleurs cmn_hans_cn dataset based on openai/whisper-small

An automatic speech recognition model fine-tuned on Cantonese dataset based on OpenAI Whisper Large V2, achieving a character error rate of 6.7274% on the test set

A Tagalog speech recognition model fine-tuned based on facebook/wav2vec2-xls-r-300m

A Cantonese fine-tuned speech recognition model based on facebook/wav2vec2-large-xlsr-53 using the Common Voice corpus version 8.0

Italian speech recognition model fine-tuned from XLS-R 1B parameter model, supports recognition with language model

A Finnish automatic speech recognition model fine-tuned based on facebook/wav2vec2-xls-r-300m, trained with 275.6 hours of Finnish annotated data, supports use with KenLM language model.

An Italian automatic speech recognition model fine-tuned on Common Voice 7 and Libri Speech datasets based on facebook/wav2vec2-xls-r-1b

This is a German automatic speech recognition model based on the XLSR Wav2Vec2 architecture, fine-tuned on the Common Voice German dataset.

XLSR-53 large model speech recognition system optimized for Polish, fine-tuned based on facebook/wav2vec2-large-xlsr-53, supports Polish automatic speech recognition

This is a Russian automatic speech recognition model based on the Wav2Vec2 XLS-R architecture with a parameter scale of 300m, evaluated on public speech and robust speech event datasets.

This model is a fine-tuned Spanish automatic speech recognition model based on facebook/wav2vec2-xls-r-300m on the COMMON_VOICE - ES dataset.

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

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

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

This is a fine-tuned XLSR-53 large model for Hungarian speech recognition tasks, trained on Common Voice and CSS10 datasets.

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

XLSR-53 large model speech recognition system optimized for Persian, fine-tuned based on facebook/wav2vec2-large-xlsr-53 architecture

An automatic speech recognition (ASR) model fine-tuned on Armenian language datasets based on facebook/wav2vec2-xls-r-300m, supporting Armenian speech-to-text tasks.

An automatic speech recognition model fine-tuned on the Common Voice Indonesian dataset based on facebook/wav2vec2-xls-r-1b

A fine-tuned version of Facebook's wav2vec2-xls-r-1b model for Finnish automatic speech recognition (ASR), trained with 259.57 hours of annotated Finnish speech data

This is an automatic speech recognition (ASR) model based on the XLS-R architecture with 300M parameters, specifically optimized for Dutch and trained on the Common Voice 8.0 dataset.

XLS-R-300M is an automatic speech recognition (ASR) model specifically optimized for Dutch, trained on the Common Voice 8 Dutch dataset.

This is an automatic speech recognition (ASR) model fine-tuned on Bulgarian speech datasets based on the facebook/wav2vec2-xls-r-300m model.