# Low-resource Speech Processing

This model is fine-tuned from MMS-300m for Arabic dialect speech recognition, capable of identifying Modern Standard Arabic and four major Arabic dialects.

The first automatic speech recognition (ASR) model specifically for the Cretan dialect, fine-tuned from the Greek XLS-R model.

A speech recognition model fine-tuned using the uob_singlish dataset based on the facebook/wav2vec2-xls-r-300m pre-trained model

This model is a fine-tuned version of wav2vec2-xls-r-300m-mixed based on the uob_singlish dataset, specializing in Singapore English speech recognition.

This model is a fine-tuned version of RuiqianLi/wav2vec2-large-xls-r-300m-singlish-colab based on the li_singlish dataset, primarily used for Singapore English speech recognition tasks.

This is an automatic speech recognition (ASR) model fine-tuned on the Turkish Common Voice dataset based on Facebook's wav2vec2-large-xlsr-53 model.

XLSR-Wav2Vec2 is a multilingual speech recognition model that learns shared speech representations through cross-lingual pretraining, supporting 53 languages.

Brazilian Portuguese Wav2vec 2.0 speech recognition model fine-tuned on the LaPS BM dataset

An Irish Gaelic automatic speech recognition model fine-tuned on wav2vec2-large-xlsr-53, trained on the Common Voice 7.0 dataset

An automatic speech recognition model fine-tuned on private datasets based on facebook/wav2vec2-xls-r-300m, featuring robust speech event processing capabilities.

HIYACCENT is a speech recognition system optimized for Nigerian English accents, built upon an enhanced Wav2Vec2 architecture with over 20% performance improvement.

DistilHuBERT is a lightweight speech representation learning model achieved through hierarchical distillation of the HuBERT model, significantly reducing model size and computational costs while maintaining performance.

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